Triple
T6271205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tap |
E140537
|
entity |
| Predicate | hasLeadCharacterOccupation |
P21567
|
FINISHED |
| Object | tap dancer |
—
|
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: tap dancer | Statement: [Tap, hasLeadCharacterOccupation, tap dancer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLeadCharacterOccupation Context triple: [Tap, hasLeadCharacterOccupation, tap dancer]
-
A.
followsCharacterOccupation
Indicates that one character’s occupation or job role comes after or succeeds another character’s occupation in a sequence or progression.
-
B.
featuresProtagonistOccupation
chosen
Indicates that the work’s main character has a specified occupation or job role.
-
C.
notableCharacterOccupation
Indicates that a notable character is associated with a specific occupation or professional role.
-
D.
hasMainRole
Indicates that an entity holds the primary or most significant role in relation to another entity or context.
-
E.
hasMainPerformerOccupation
Indicates that an entity’s primary or main performer is associated with a specified occupation or professional role.
- 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_69c008cabc4081909723e2547c9d6cc0 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063bb340c8190ab81b249cefa91ca |
completed | March 22, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69c05606fb50819082d1a5a91e5030b6 |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:25 p.m.