Triple
T16334129
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martin Ritt |
E396631
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Norma Rae |
E659780
|
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: Norma Rae | Statement: [Martin Ritt, directed, Norma Rae]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Norma Rae Context triple: [Martin Ritt, directed, Norma Rae]
-
A.
Norma Rae
chosen
Norma Rae is a 1979 American drama film starring Sally Field as a Southern textile worker who becomes a key figure in a labor union organizing effort.
-
B.
Dolly Wilcox
Dolly Wilcox is a member of the Wilcox family, a fictional upper-middle-class English family central to E.M. Forster’s novel "Howards End."
-
C.
Norma Jennings
Norma Jennings is a kind-hearted diner owner in the cult television series "Twin Peaks," known for her moral integrity and complicated romantic life.
-
D.
Janie Bradford
Janie Bradford is an American songwriter best known for co-writing the Motown hit "Money (That's What I Want)" and contributing to the label's early success.
-
E.
Maxine Sneed
Maxine Sneed is a Canadian editor and the former wife of comedian and actor Tommy Chong.
- 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2c4e1da1081909bec6e77e6109dce |
completed | April 17, 2026, 11:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002dabc89481908005f5b2060abded |
completed | May 10, 2026, 7:03 a.m. |
Created at: April 10, 2026, 5:07 a.m.