Triple
T20502505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mike Salisbury |
E503340
|
entity |
| Predicate | workOn |
P30363
|
FINISHED |
| Object | Meat Eaters |
—
|
NE NERFINISHED |
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: Meat Eaters | Statement: [Mike Salisbury, workOn, Meat Eaters]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Meat Eaters Context triple: [Mike Salisbury, workOn, Meat Eaters]
-
A.
Meat Eaters
chosen
"Meat Eaters" is an episode of the BBC nature documentary series *The Life of Mammals* that explores the behavior, adaptations, and ecology of carnivorous mammals.
-
B.
Meathead
Meathead is the derisive nickname given to Michael Stivic, the liberal, college-educated son-in-law of Archie Bunker on the classic American sitcom "All in the Family."
-
C.
Big Meat
Big Meat is a supporting criminal figure in the 2006 action-crime film "Waist Deep."
-
D.
The Beef Carcass
The Beef Carcass is a vivid, expressionistic painting by Chaim Soutine, renowned for its dramatic depiction of a hanging animal carcass that explores themes of mortality and raw physicality.
-
E.
All That Meat and No Potatoes
"All That Meat and No Potatoes" is a jazz standard composed by Fats Waller, known for its playful lyrics and swinging, stride-influenced style.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4b1e52c8190894281cf7e3283ab |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69dc272a481909329ecd1560989ef |
completed | April 20, 2026, 9:42 p.m. |
Created at: April 16, 2026, 11:35 a.m.