Triple
T15064004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | On Deadly Ground |
E379708
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Ed Horowitz |
E594169
|
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: Ed Horowitz | Statement: [On Deadly Ground, screenwriter, Ed Horowitz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ed Horowitz Context triple: [On Deadly Ground, screenwriter, Ed Horowitz]
-
A.
Ed Horowitz
chosen
Ed Horowitz is a screenwriter best known for co-writing the action film "Exit Wounds."
-
B.
Scott Gilman
Scott Gilman is a musician best known as a member of the British-American rock band Foreigner.
-
C.
Christopher Jarecki
Christopher Jarecki is an American musician and radio show host best known as the former husband of actress Alicia Silverstone.
-
D.
Howard Gordon
Howard Gordon is an American television writer and producer best known for his work on acclaimed series such as "24" and "Homeland."
-
E.
Jeremy Leven
Jeremy Leven is an American screenwriter, director, and novelist known for adapting romantic and character-driven stories for film, including the hit movie "The Notebook."
- 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_69d85cd7683881908d405c1b5d7b4f7f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dedee803ac81908bb7d66e49c2eb72 |
completed | April 15, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fea5c8b3ac8190b8fc921b6e6eeed5 |
completed | May 9, 2026, 3:11 a.m. |
Created at: April 10, 2026, 3:02 a.m.