Om + te-infinitivals are formally characterized by the presence of the infinitival marker te and the complementizer-like element om. There are at least two analyses available for the infinitival marker te. According to some proposals te is a bound morpheme prefixed to the infinitival verb, just like ge- is a bound morpheme in past participle forms like ge-pak-t'taken'. This may account for the fact that both te and ge- are normally adjacent to the stem of the verb. An alternative proposal is that te is the T(ense) head of the functional projection TP. We refer the reader to Section 1.3, sub IIIA1, and references cited there for a more extensive discussion of these proposals.
      One reason for assuming that the element om is a complementizer, and not a preposition, is that infinitival complement clauses introduced by this element behave like finite complement clauses and not like PP-complements in that they must be in extraposed position, that is, they obligatorily follow the matrix verb in clause-final position. This can be illustrated by means of the embedded and the perfect-tense counterparts of example (30a), which are given in (31).

Further grounds for assuming that om is a complementizer are that it can often be omitted, as illustrated in (32a). This would be quite surprising for a preposition, but it is attested for complementizers in many languages: cf. John promised (that) he would send Elisabeth the book. Another reason for assuming we are not dealing with a PP-complement is that the infinitival clause is not pronominalized by means of the pronominal PP erom but by the pronoun dat; this is illustrated in (32b).

It should be noted, however, that the omission of om is not syntactically innocuous; the examples in (33) show that it may make the infinitival clause transparent for extraction of the object to a position to the left of the matrix verb in the matrix clause; see Section 4.4.3 for more detailed discussion. The percentage sign in (33b) is added because some speakers object to such examples.

The fact that this type of extraction is excluded from finite clauses such as (34a) suggests that om + te-infinitivals and finite clauses are of the same categorial type; they are CPs. Infinitival clauses without om, on the other hand, are likely to be less extended verbal projections, which would make TP a likely candidate. See Section 9.1 for an introduction to the functional categories CP and TP.

For completeness' sake, note that the string Jan heeft het boek beloofd dat hij naar Els zal sturen is acceptable if the postverbal clause is interpreted as a relative clause modifying het boek ("John promised the book that he will bring to Els"), but this is of course irrelevant here.