Triple
T15026388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lethal Weapon 3 |
E378226
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Stuart Wilson |
E993455
|
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: Stuart Wilson | Statement: [Lethal Weapon 3, starring, Stuart Wilson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stuart Wilson Context triple: [Lethal Weapon 3, starring, Stuart Wilson]
-
A.
Stuart Wilson
chosen
Stuart Wilson is a British actor known for his work in film, television, and theatre, often appearing in dramatic and period roles.
-
B.
Stuart Thompson
Stuart Thompson was a prominent Broadway theatre producer known for backing numerous successful plays and musicals.
-
C.
Stuart Morrison
Stuart Morrison is a motorsport communications professional who serves as the head of communications for the Haas Formula 1 Team.
-
D.
Stuart Gharty
Stuart Gharty is a fictional Baltimore police detective featured as a main character on the television drama series "Homicide: Life on the Street."
-
E.
Stuart Warren
Stuart Warren is known primarily as the husband of American actress and businesswoman Sara Shane.
- 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_69d85cd46b2c819090d054c27787f677 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7dfcb508190aec8cd667e27a8ea |
completed | April 15, 2026, 12:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feae09dca88190a832e1b068252137 |
completed | May 9, 2026, 3:46 a.m. |
Created at: April 10, 2026, 2:58 a.m.