Triple
T15393163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | To Catch a Killer |
E368099
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Tom Lazarus |
E1079266
|
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: Tom Lazarus | Statement: [To Catch a Killer, writer, Tom Lazarus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Lazarus Context triple: [To Catch a Killer, writer, Tom Lazarus]
-
A.
Tom Lazarus
chosen
Tom Lazarus is an American screenwriter and television writer best known for his work on the supernatural horror film "Stigmata" and various genre TV series.
-
B.
Sam Lash
Sam Lash is a fictional character appearing in the literary work "The Wolf Song."
-
C.
John LaRue
John LaRue was an early American pioneer and landowner in Kentucky after whom LaRue County was named.
-
D.
Wolf Leslau
Wolf Leslau was a prominent linguist and scholar of Semitic and Ethiopian languages, renowned for his extensive fieldwork and documentation of endangered tongues.
-
E.
Louis Osbourne
Louis Osbourne is a British DJ, producer, and media personality best known as the son of rock musician Ozzy Osbourne and for his appearances on the reality show "The Osbournes."
- 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_69d85a1551a08190ba2caea7cd51c639 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e7838b48190862b43c6c8620692 |
completed | April 16, 2026, 1:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff1350699c8190acf7830d88455851 |
completed | May 9, 2026, 10:58 a.m. |
Created at: April 10, 2026, 3:19 a.m.