Triple
T23415408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dancing Lady |
E560191
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Allen Rivkin |
—
|
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: Allen Rivkin | Statement: [Dancing Lady, screenwriter, Allen Rivkin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Allen Rivkin Context triple: [Dancing Lady, screenwriter, Allen Rivkin]
-
A.
Allen Rivkin
chosen
Allen Rivkin was an American screenwriter active during Hollywood’s studio era, known for his work on numerous mid-20th-century films.
-
B.
Michael Glouberman
Michael Glouberman is a television writer and producer best known for his work on the acclaimed sitcom "Malcolm in the Middle."
-
C.
Jeffrey Cohen
Jeffrey Cohen is a songwriter best known for co-writing the theme song to the James Bond film "Licence to Kill."
-
D.
Paul Goldstein
Paul Goldstein is a prominent American legal scholar and author, best known for his influential work in intellectual property and copyright law.
-
E.
Paul Goldstein
Paul Goldstein is a former American professional tennis player who became the head coach of the Stanford Cardinal men’s tennis team.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a514b1d08190bbde2c3714c996fd |
completed | April 29, 2026, 6:28 a.m. |
Created at: April 17, 2026, 5:39 p.m.