Triple
T22996413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | de Castro |
E572205
|
entity |
| Predicate | usesPrepositionalParticle |
P63950
|
FINISHED |
| Object | de |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: de | Statement: [de Castro, usesPrepositionalParticle, de]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesPrepositionalParticle Context triple: [de Castro, usesPrepositionalParticle, de]
-
A.
hasPreposition
chosen
Indicates that one entity is associated with or linked to another entity through a specific prepositional relationship.
-
B.
usesPostpositions
Indicates that one entity employs postpositions, placing relational or grammatical markers after the words they modify rather than before them.
-
C.
hasPrepositions
Indicates that one entity includes, uses, or is associated with one or more prepositions in relation to another entity.
-
D.
hasPrepositionalPrefix
Indicates that one entity functions as a prepositional prefix attached to or modifying another entity.
-
E.
hasDiscourseParticle
Indicates that one element functions as a discourse particle in relation to another within a communicative or textual context.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e245b535808190adef8a9df3c584db |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182f3186c81909e0d5177029a72ae |
completed | April 29, 2026, 4:02 a.m. |
| PD | Predicate disambiguation | batch_69ef3b974e7c8190b8be11dbb4518693 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:50 p.m.