Triple
T18598378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Exit Wounds |
E454553
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | John Hart |
—
|
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: John Hart | Statement: [Exit Wounds, featuresCharacter, John Hart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Hart Context triple: [Exit Wounds, featuresCharacter, John Hart]
-
A.
John Hart
John Hart is a film producer best known for his work on literary adaptations and independent movies, including the 2002 adaptation of "Nicholas Nickleby."
-
B.
John Hart
John Hart is the son of former U.S. Senator and 1980s Democratic presidential contender Gary Hart.
-
C.
John Hart
chosen
John Hart was an American actor best known for temporarily taking over the title role in the classic television Western series "The Lone Ranger" in the early 1950s.
-
D.
Jeffrey Konvitz
Jeffrey Konvitz is an American author and film producer best known for his 1974 horror novel "The Sentinel," which was adapted into a feature film.
-
E.
Peter Barton
Peter Barton is an American actor best known for his roles in 1980s horror and television series, including a prominent part in the slasher film "Friday the 13th: The Final Chapter."
- 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_69d8d38ae7e081908a98df1251842402 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5474d934481909b4afd5ef9031c73 |
completed | April 19, 2026, 9:21 p.m. |
Created at: April 10, 2026, 11:44 a.m.