Triple
T11345559
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mandy Patinkin |
E268702
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Yentl |
E125958
|
NE 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: Yentl | Statement: [Mandy Patinkin, notableWork, Yentl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yentl Context triple: [Mandy Patinkin, notableWork, Yentl]
-
A.
Yentl (1983 film)
chosen
Yentl (1983 film) is a musical drama directed by and starring Barbra Streisand, about a young Jewish woman in early 20th-century Eastern Europe who disguises herself as a man to pursue religious education.
-
B.
Written on the Wind
Written on the Wind is a 1956 Technicolor melodrama directed by Douglas Sirk, renowned for its lush visual style and emotionally charged tale of a wealthy Texas oil family’s turmoil.
-
C.
Gilda
Gilda is a classic 1946 American film noir starring Rita Hayworth in one of her most iconic roles.
-
D.
Gilda
Gilda is the witty, free-spirited woman at the center of Noël Coward’s play "Design for Living," entangled in a complex romantic triangle.
-
E.
National Velvet
National Velvet is a classic 1944 family sports drama film about a young girl and her horse competing in the Grand National steeplechase.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7ea1f9574819089760c5b5908f09e |
completed | April 9, 2026, 6:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5436e9d848190a7e585351d24df03 |
completed | April 19, 2026, 9:04 p.m. |
Created at: April 8, 2026, 9:33 p.m.