Triple
T15080162
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geoffrey Lewis |
E380117
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Matlock |
E424732
|
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: Matlock | Statement: [Geoffrey Lewis, notableWork, Matlock]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matlock Context triple: [Geoffrey Lewis, notableWork, Matlock]
-
A.
Matlock
Matlock is a historic spa and market town in Derbyshire, England, known for its picturesque setting in the Derwent Valley and its role as the county’s administrative centre.
-
B.
Matlock
chosen
Matlock is an American legal drama television series starring Andy Griffith as a shrewd, folksy defense attorney known for his courtroom showdowns and investigative skills.
-
C.
Kojak
Kojak is a 1970s American television crime drama series centered on the tough, lollipop-licking New York City detective Theo Kojak, played by Telly Savalas.
-
D.
Van der Valk
Van der Valk is a British television crime drama series centered on a Dutch detective solving cases in Amsterdam.
-
E.
Mannix
Mannix is an American television detective series from the late 1960s and 1970s, centered on the tough, resourceful private investigator Joe Mannix.
- 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_69d85cd7683881908d405c1b5d7b4f7f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dff80008c88190840f94222f867478 |
completed | April 15, 2026, 8:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feae15d6308190a62b4f66c550db04 |
completed | May 9, 2026, 3:46 a.m. |
Created at: April 10, 2026, 3:03 a.m.