Triple
T13790766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Theodore Levine |
E331388
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Ted Levine |
E65187
|
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: Ted Levine | Statement: [Frank Theodore Levine, name, Ted Levine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ted Levine Context triple: [Frank Theodore Levine, name, Ted Levine]
-
A.
Ted Levine
chosen
Ted Levine is an American character actor best known for his chilling portrayal of serial killer Buffalo Bill in the film "The Silence of the Lambs."
-
B.
Brian Reynolds
Brian Reynolds is a technology entrepreneur best known as a founder of the enterprise software company Micro Focus.
-
C.
Warren Spector
Warren Spector is an influential American video game designer and producer best known for pioneering immersive sim titles such as Deus Ex and System Shock.
-
D.
Neil Druckmann
Neil Druckmann is a video game writer, director, and executive at Naughty Dog best known for co-creating and writing The Last of Us franchise and its television adaptation.
-
E.
Richard Devine
Richard Devine is an American electronic musician and sound designer known for his complex, experimental compositions and work in film, games, and technology.
- 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_69d81c58feb08190a77bca8bf7d6d20f |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de024af32c8190a9bd1278e09564ba |
completed | April 14, 2026, 9 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b07f5cf48190b59827efb5918a95 |
completed | May 3, 2026, 8:30 p.m. |
Created at: April 9, 2026, 10:11 p.m.