Triple
T33393403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Wayne as Rooster Cogburn |
E855109
|
entity |
| Predicate | coStarInRoosterCogburn |
P128430
|
FINISHED |
| Object | Katharine Hepburn |
—
|
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: Katharine Hepburn | Statement: [John Wayne as Rooster Cogburn, coStarInRoosterCogburn, Katharine Hepburn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coStarInRoosterCogburn Context triple: [John Wayne as Rooster Cogburn, coStarInRoosterCogburn, Katharine Hepburn]
-
A.
coStar
Indicates that two or more performers appear together in the same production in significant acting roles.
-
B.
co-star
Indicates that two or more performers appear together in the same production, sharing significant acting roles.
-
C.
coResident
Indicates that two or more entities live in the same residence or dwelling at the same time.
-
D.
coEscapee
Indicates that two or more entities escaped together from the same place or situation.
-
E.
costarWith
chosen
Indicates that two performers appear together as significant cast members in the same production, such as a film, television show, or stage performance.
- 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_69f3496e3f1c8190bcecfa82aa9d17ff |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f8164698819090c1b471f1caa4c6 |
completed | May 3, 2026, 7:24 a.m. |
| PD | Predicate disambiguation | batch_69f6f6619404819084662aef1238261c |
completed | May 3, 2026, 7:16 a.m. |
Created at: May 1, 2026, 1:35 a.m.