Triple
T16909979
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hercules (1997 film) |
E410168
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Don McEnery |
—
|
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: Don McEnery | Statement: [Hercules (1997 film), screenwriter, Don McEnery]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Don McEnery Context triple: [Hercules (1997 film), screenwriter, Don McEnery]
-
A.
Donald McEnery
chosen
Donald McEnery is an American screenwriter best known for co-writing the Pixar animated film "A Bug's Life."
-
B.
Bill Rigney
Bill Rigney was an American Major League Baseball manager and former infielder best known for managing teams such as the New York/San Francisco Giants, Los Angeles/California Angels, and Minnesota Twins.
-
C.
Jim McKelvey
Jim McKelvey is an American entrepreneur and co-founder of the financial technology company Square (now Block, Inc.), as well as a philanthropist and author.
-
D.
Ted Cheesman
Ted Cheesman was a film editor best known for his work on classic Hollywood productions, including the 1933 monster film "King Kong."
-
E.
Brian Boland
Brian Boland is an American actor best known for his role in the horror film "Paranormal Activity 2."
- 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_69d886c7b1e481908c3766dfa8c13458 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3ca3bdc3081908a9b4f6e63405348 |
completed | April 18, 2026, 6:15 p.m. |
Created at: April 10, 2026, 5:30 a.m.