Triple
T14955623
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Koechner |
E372916
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Extract |
E81056
|
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: Extract | Statement: [David Koechner, notableWork, Extract]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Extract Context triple: [David Koechner, notableWork, Extract]
-
A.
Extract
chosen
Extract is a 2009 comedy film written and directed by Mike Judge that satirizes workplace and personal frustrations at a flavor-extract factory.
-
B.
EX
EX is a UK postcode area covering Exeter and surrounding parts of Devon.
-
C.
Extra
Extra is a popular sugar-free chewing gum brand produced by the Wrigley Company, known for its long-lasting flavor and wide variety of mint and fruit options.
-
D.
Extra
Extra is an American entertainment news television program that covers celebrity news, gossip, and pop culture.
-
E.
Eext
Eext is a small village in the Dutch province of Drenthe, known for its rural character and surrounding natural landscapes.
- 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_69d85cca979481908747d2a81eba1cea |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6cc73848190ac181782b20dc838 |
completed | April 15, 2026, 12:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe7e9c71cc8190aff9165a6f97981a |
completed | May 9, 2026, 12:23 a.m. |
Created at: April 10, 2026, 2:40 a.m.