Triple
T17272750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zawe Ashton |
E419304
|
entity |
| Predicate | appearedIn |
P795
|
FINISHED |
| Object | Fresh Meat |
E592631
|
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: Fresh Meat | Statement: [Zawe Ashton, appearedIn, Fresh Meat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fresh Meat Context triple: [Zawe Ashton, appearedIn, Fresh Meat]
-
A.
Fresh Meat
chosen
Fresh Meat is a British comedy-drama television series that follows the chaotic lives of a group of university students sharing a house in Manchester.
-
B.
Meat Eaters
"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.
-
C.
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."
-
D.
Big Meat
Big Meat is a supporting criminal figure in the 2006 action-crime film "Waist Deep."
-
E.
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.
- 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_69d886da626481908a14ce7830329a35 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42f4b023c8190b92df4015c14c3a8 |
completed | April 19, 2026, 1:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0180d08c9c8190ae139cd92720028a |
completed | May 11, 2026, 7:10 a.m. |
Created at: April 10, 2026, 5:40 a.m.