Triple
T16826861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Cheek |
E409040
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Cheek |
E978348
|
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: Cheek | Statement: [Tom Cheek, familyName, Cheek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cheek Context triple: [Tom Cheek, familyName, Cheek]
-
A.
Cheek
chosen
Cheek is a surname of English origin borne by various notable individuals across fields such as politics, academia, and the arts.
-
B.
Jaw
Jaw is a coastal village in Bahrain known for its beaches and the nearby Jaw Prison, one of the country’s main detention facilities.
-
C.
Grimace
Grimace is a large, purple, friendly character from the McDonaldland universe who appears in McDonald's advertising and promotions.
-
D.
Lips
Lips is a Dutch surname borne by various individuals, including those of Flemish and Dutch origin.
-
E.
Cheeky
Cheeky is a film directed by British actor and filmmaker David Thewlis.
- 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_69d88394566c8190b3dcbdc72935f7fa |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b31404c88190a3b2802842ca77eb |
completed | April 18, 2026, 4:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00b29e48f881908489bd77a9caec97 |
completed | May 10, 2026, 4:30 p.m. |
Created at: April 10, 2026, 5:23 a.m.