Triple
T22128590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fat |
E546851
|
entity |
| Predicate | hasLivePerformanceCostume |
P24550
|
FINISHED |
| Object | inflatable fat suit |
—
|
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: inflatable fat suit | Statement: [Fat, hasLivePerformanceCostume, inflatable fat suit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLivePerformanceCostume Context triple: [Fat, hasLivePerformanceCostume, inflatable fat suit]
-
A.
hasLivePerformanceStyle
Indicates that an entity is associated with a particular style or manner of live performance.
-
B.
isCostumed
chosen
Indicates that an entity is wearing or otherwise adorned with a costume.
-
C.
isCostumedCharacterFor
Indicates that one entity serves as a costumed character representation or mascot for another entity, typically for promotional or entertainment purposes.
-
D.
livePerformanceStapleFor
Indicates that something (such as a song or piece) is regularly and prominently featured in another entity’s live performances.
-
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_69e11e39bf348190b541bfa16a7b71e0 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12983acfc81908013f66acb31f198 |
completed | April 28, 2026, 9:41 p.m. |
| PD | Predicate disambiguation | batch_69e71b384e008190b723c9a0f1089d66 |
completed | April 21, 2026, 6:37 a.m. |
Created at: April 16, 2026, 8:32 p.m.