Triple
T7037432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matthew Gregory |
E163417
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Mad Cows |
E119027
|
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: Mad Cows | Statement: [Matthew Gregory, notableWork, Mad Cows]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mad Cows Context triple: [Matthew Gregory, notableWork, Mad Cows]
-
A.
Mad Cows
chosen
Mad Cows is a 1999 British comedy film about a chaotic series of misadventures involving a young mother entangled in crime and bureaucracy.
-
B.
Mad Cowgirl
Mad Cowgirl is a 2006 surreal, low-budget independent horror-thriller film known for its bizarre narrative and cult appeal.
-
C.
Concrete Cows
Concrete Cows is a famous outdoor sculpture in Milton Keynes consisting of life-sized cow figures made from concrete and fiberglass, often seen as an iconic symbol of the town.
-
D.
The Cow
The Cow is the English title of Surah Al-Baqarah, the Quran’s longest chapter, which covers core themes of faith, law, guidance, and the relationship between God and humanity.
-
E.
The Cow
The Cow is a landmark 1969 Iranian drama film directed by Dariush Mehrjui that is widely credited with helping launch the Iranian New Wave.
- 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_69c6885e7c1c8190be32a8f79ab4e0cf |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e221a7988190b6b69782a275abb7 |
completed | March 27, 2026, 8:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c775a6e1a08190af7d121cb854118e |
completed | March 28, 2026, 6:31 a.m. |
Created at: March 27, 2026, 2:36 p.m.