Triple
T15368718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deliver Us from Evil |
E367485
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Paul Harris Boardman |
E927986
|
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: Paul Harris Boardman | Statement: [Deliver Us from Evil, screenwriter, Paul Harris Boardman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Harris Boardman Context triple: [Deliver Us from Evil, screenwriter, Paul Harris Boardman]
-
A.
Paul Harris Boardman
chosen
Paul Harris Boardman is an American screenwriter and producer best known for his work on horror and supernatural films such as "The Exorcism of Emily Rose."
-
B.
James Burrows
James Burrows is an American television director and producer best known for his influential work on classic sitcoms such as "Cheers," "Taxi," and "Will & Grace."
-
C.
Charles Harris
Charles Harris was a notable figure in Georgia’s early history, honored as the namesake of Harris County.
-
D.
Peter Milne
Peter Milne was a screenwriter known for his work on classic Hollywood films, including the legal drama "The Verdict."
-
E.
Tony Bancroft
Tony Bancroft is an American animator and film director best known for co-directing Disney’s animated feature "Mulan."
- 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_69d85a1483788190ad93c2748e8af34b |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e4b88a881909f9575c02aed287d |
completed | April 16, 2026, 1:41 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff0b50703881909ca71c985bc1c7b5 |
completed | May 9, 2026, 10:24 a.m. |
Created at: April 10, 2026, 3:18 a.m.