Triple
T12781314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reach for the Sky |
E305512
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Vernon Harris |
E912336
|
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: Vernon Harris | Statement: [Reach for the Sky, screenwriter, Vernon Harris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vernon Harris Context triple: [Reach for the Sky, screenwriter, Vernon Harris]
-
A.
Vernon Harris
chosen
Vernon Harris was a British screenwriter best known for his work on the film adaptation of the musical "Oliver!"
-
B.
Vernon Layton
Vernon Layton is a cinematographer best known for his work on the horror-comedy film "Seed of Chucky."
-
C.
Vic Harris
Vic Harris was a prominent Negro league baseball figure best known for managing the powerhouse Homestead Grays during their era of dominance.
-
D.
Vernon March
Vernon March was a British sculptor best known for creating major public monuments and war memorials in the early 20th century.
-
E.
John Vickery
John Vickery is an American actor known for his work in film, television, and theater, including notable roles in genre series and stage productions.
- 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_69d7bdf2b43c819098ae5aa68e61ea58 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e5b52048190b279b7ad066efe9f |
completed | April 10, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6a5427be88190956c616b832d9841 |
completed | May 3, 2026, 1:30 a.m. |
Created at: April 9, 2026, 5:29 p.m.