Triple
T31973821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dorothy (Thief) |
E816392
|
entity |
| Predicate | hasLeadActorCoStar |
P129510
|
FINISHED |
| Object | James Caan |
—
|
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: James Caan | Statement: [Dorothy (Thief), hasLeadActorCoStar, James Caan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLeadActorCoStar Context triple: [Dorothy (Thief), hasLeadActorCoStar, James Caan]
-
A.
associatedWithLeadActorOfFilm
Indicates a relationship where one entity is connected or linked in some relevant way to the lead actor of a specified film.
-
B.
filmCoStar
chosen
Indicates that two people appeared together as co-actors in the same film.
-
C.
hasSiblingCoStars
Indicates that two or more entities have appeared together as co-stars and are siblings in relation to each other.
-
D.
starredActorWith
Indicates that one entity participated as an actor in a production together with another specified actor.
-
E.
associatedWithLeadActorsOfSeries
Indicates a relationship where something or someone is connected or linked to the lead actors of a television or film series.
- 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_69f348f5ae5481909da0247869f51955 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd4f39b5008190b83b3227ce22c509 |
completed | May 8, 2026, 2:49 a.m. |
| PD | Predicate disambiguation | batch_69fd4df17c548190a4e2a6fea70f7e10 |
completed | May 8, 2026, 2:44 a.m. |
Created at: May 1, 2026, 12:10 a.m.