Triple
T23098943
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fame (1980 film) |
E575972
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Christopher Gore |
—
|
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: Christopher Gore | Statement: [Fame (1980 film), screenwriter, Christopher Gore]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Christopher Gore Context triple: [Fame (1980 film), screenwriter, Christopher Gore]
-
A.
Christopher Gore
Christopher Gore was an American lawyer, Federalist politician, and governor of Massachusetts in the early 19th century.
-
B.
Christopher Gore
chosen
Christopher Gore was an American screenwriter and playwright best known for creating and developing the musical film and subsequent TV adaptations of "Fame."
-
C.
Paul Gore
Paul Gore is a British music video director known for his visually distinctive work with prominent artists across various genres.
-
D.
Chris Hartnett
Chris Hartnett is an American entrepreneur and former telecommunications executive best known for his success in the domain name industry and as a prominent figure in early internet business ventures.
-
E.
Paul Gillmor
Paul Gillmor was an American Republican politician who served for nearly two decades as a U.S. Representative from Ohio.
- 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18de71a088190b91918e6c4ea6e97 |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:58 p.m.