Triple
T33915231
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Professor Corey |
E869431
|
entity |
| Predicate | hasStageCostumeElement |
P28106
|
FINISHED |
| Object | tousled hair |
—
|
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: tousled hair | Statement: [Professor Corey, hasStageCostumeElement, tousled hair]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStageCostumeElement Context triple: [Professor Corey, hasStageCostumeElement, tousled hair]
-
A.
costumeElement
chosen
Indicates that one item functions as a component or part of another item's costume.
-
B.
stageCostume
Indicates that one entity is a costume specifically used or worn for a performance or stage production by another entity.
-
C.
hasCostumes
Indicates that one entity possesses, provides, or is associated with one or more costumes.
-
D.
hasStageDesignElement
Indicates a relationship in which a stage production, performance, or set includes or is associated with a particular stage design element (such as props, scenery, lighting, or other visual components).
-
E.
haveDistinctCostume
Indicates that the entities each possess a costume that is different from the others’ costumes.
- 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_69f3499869bc8190b6c33a81686af226 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff6fba1a5c8190a660279a6271d785 |
completed | May 9, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69ff6f59388c8190a7d6ab7bc7705bc0 |
completed | May 9, 2026, 5:31 p.m. |
Created at: May 1, 2026, 1:48 a.m.