Triple
T37822178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Now or Never |
E942947
|
entity |
| Predicate | starsComedian |
P185309
|
FINISHED |
| Object | Harold Lloyd |
—
|
NE NERFINISHED |
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: Harold Lloyd | Statement: [Now or Never, starsComedian, Harold Lloyd]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: starsComedian Context triple: [Now or Never, starsComedian, Harold Lloyd]
-
A.
starsComedianKnownFor
Indicates that a work features a comedian who is particularly recognized or famous for that role or performance.
-
B.
comedian
Indicates that the subject performs comedy or is recognized for engaging in comedic entertainment.
-
C.
hasLeadComedian
chosen
Indicates that one entity serves as the primary or main comedian associated with another entity, such as a show, event, or performance.
-
D.
starredActor
Indicates that an actor performed a leading or significant role in a particular production or work.
-
E.
hasComedyShows
Indicates that one entity offers, features, or includes comedy shows associated with another entity.
- 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_69f76ee987588190906506e759be5db3 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbbae559a8819086ef839973f8d9b2 |
completed | May 6, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69fbb1440fa08190abf25ba684f75b6e |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:19 p.m.