Triple
T18330631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Insatiable |
E439127
|
entity |
| Predicate | executiveProducer |
P7225
|
FINISHED |
| Object | Nina Wass |
—
|
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: Nina Wass | Statement: [Insatiable, executiveProducer, Nina Wass]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nina Wass Context triple: [Insatiable, executiveProducer, Nina Wass]
-
A.
Nina Wass
chosen
Nina Wass is a television producer known for her executive work on drama series such as "Shades of Blue."
-
B.
Nina Martin
Nina Martin is a fictional character appearing in the crime film "The Crooked Way."
-
C.
Nina Fock
Nina Foch was a Dutch-born American actress and acting teacher known for her roles in classic films such as "An American in Paris," "The Ten Commandments," and "Executive Suite."
-
D.
Nina Stevens
Nina Stevens is the wife of Canadian businessman and former federal cabinet minister Sinclair Stevens.
-
E.
Nina
Nina is a feminine given name used in various cultures, often as a short form of names like Antonina or Giannina, and borne by numerous notable figures in the arts and public life.
- 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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50ec900808190bc4468270e0957c1 |
completed | April 19, 2026, 5:20 p.m. |
Created at: April 10, 2026, 10:36 a.m.