Triple
T23018569
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hold Back the Night |
E573101
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
Jack DeWitt
Jack DeWitt was an American screenwriter known for his work on mid-20th-century films, particularly war and adventure movies.
|
E1568212
|
NE FINISHED |
How this triple was built (4 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: Jack DeWitt | Statement: [Hold Back the Night, screenwriter, Jack DeWitt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jack DeWitt Context triple: [Hold Back the Night, screenwriter, Jack DeWitt]
-
A.
Jack Deerson
Jack Deerson is a cinematographer best known for his work on the 1971 road movie "Two-Lane Blacktop."
-
B.
Lew DeWitt
Lew DeWitt was an American country and gospel singer, guitarist, and founding tenor of the Statler Brothers, known for his smooth high harmonies and songwriting.
-
C.
Wallace DeWitt
Wallace DeWitt was a U.S. Army medical officer honored for his service and leadership in military medicine, for whom DeWitt Army Community Hospital is named.
-
D.
Michael Dilbeck
Michael Dilbeck is a film producer best known for his work on the comedy movie "Meet Wally Sparks."
-
E.
Charlie Decker
Charlie Decker is the troubled teenage protagonist of Stephen King’s early novel "Rage," known for his violent classroom hostage-taking and psychological unraveling.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Jack DeWitt Triple: [Hold Back the Night, screenwriter, Jack DeWitt]
Generated description
Jack DeWitt was an American screenwriter known for his work on mid-20th-century films, particularly war and adventure movies.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jack DeWitt Target entity description: Jack DeWitt was an American screenwriter known for his work on mid-20th-century films, particularly war and adventure movies.
-
A.
Jack Deerson
Jack Deerson is a cinematographer best known for his work on the 1971 road movie "Two-Lane Blacktop."
-
B.
Lew DeWitt
Lew DeWitt was an American country and gospel singer, guitarist, and founding tenor of the Statler Brothers, known for his smooth high harmonies and songwriting.
-
C.
Wallace DeWitt
Wallace DeWitt was a U.S. Army medical officer honored for his service and leadership in military medicine, for whom DeWitt Army Community Hospital is named.
-
D.
Michael Dilbeck
Michael Dilbeck is a film producer best known for his work on the comedy movie "Meet Wally Sparks."
-
E.
Charlie Decker
Charlie Decker is the troubled teenage protagonist of Stephen King’s early novel "Rage," known for his violent classroom hostage-taking and psychological unraveling.
- F. None of above. chosen
Provenance (5 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e64a4c8190b8d29ed638c7fef8 |
completed | April 29, 2026, 4:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c0accf39c8190b66c4b7d2b32dfb0 |
completed | May 19, 2026, 7:01 a.m. |
| NEDg | Description generation | batch_6a0c0b9d0ad48190b0bd0c19876e6af2 |
completed | May 19, 2026, 7:05 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c0d995ea081908dd9d09d6d63ddfe |
completed | May 19, 2026, 7:13 a.m. |
Created at: April 17, 2026, 3:52 p.m.