Triple
T19033219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lennie Briscoe |
E465797
|
entity |
| Predicate | partner |
P1136
|
FINISHED |
| Object | Ed Green |
—
|
NE NERFINISHED |
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: Ed Green | Statement: [Lennie Briscoe, partner, Ed Green]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ed Green Context triple: [Lennie Briscoe, partner, Ed Green]
-
A.
Ed Green
chosen
Ed Green is a fictional New York City homicide detective on the television series "Law & Order," known for his sharp instincts, moral complexity, and long-running partnership with senior detectives.
-
B.
Steve Edwards
Steve Edwards is a British singer and songwriter best known for providing vocals on several popular house and dance tracks, including collaborations with artists like Bob Sinclar.
-
C.
Steve Edwards
Steve Edwards is the benefactor after whom Murray Edwards College at the University of Cambridge is named.
-
D.
Steve Edwards
Steve Edwards is a film editor best known for his work on major Hollywood productions, including the adventure-comedy sequel "Jumanji: The Next Level."
-
E.
Tony Green
Tony Green is a voice actor best known for providing the voice of the Marvel Comics villain Bullseye in animated media.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd0359648190bc2a9202c5cf29d2 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d741cabc8190900e12265ad269f8 |
completed | April 20, 2026, 7:35 a.m. |
Created at: April 10, 2026, 12:02 p.m.