Triple
T20661478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Needful Things |
E507768
|
entity |
| Predicate | filmAdaptationStar |
P795
|
FINISHED |
| Object | Ed Harris |
—
|
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: Ed Harris | Statement: [Needful Things, filmAdaptationStar, Ed Harris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ed Harris Context triple: [Needful Things, filmAdaptationStar, Ed Harris]
-
A.
Ed Harris
chosen
Ed Harris is an American actor and filmmaker known for his intense, authoritative performances in films such as "The Truman Show," "Apollo 13," and "Pollock."
-
B.
Martin Shaw
Martin Shaw is a British actor known for his extensive work in television, film, and theatre, including prominent roles in series such as "The Professionals" and "Judge John Deed."
-
C.
Martin Shaw
Martin Shaw is a fictional character from the psychological horror film "Seven Days to Live."
-
D.
Michael York
Michael York is an English actor known for his roles in films such as "Cabaret," "Logan's Run," and the "Austin Powers" series.
-
E.
Eric S. Roberts
Eric S. Roberts is a prominent computer scientist and educator known for his influential work in computer science pedagogy, curriculum development, and widely used textbooks.
- 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_69e0b4c059bc81908ea762cd73ea4424 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6b2f2ee4081908df9ba897c9dfc98 |
completed | April 20, 2026, 11:12 p.m. |
Created at: April 16, 2026, 11:44 a.m.