Triple
T3189780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neil Goldman |
E66791
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Mort Goldman |
E58012
|
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: Mort Goldman | Statement: [Neil Goldman, associatedWith, Mort Goldman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mort Goldman Context triple: [Neil Goldman, associatedWith, Mort Goldman]
-
A.
Mort Goldman
chosen
Mort Goldman is a neurotic, bespectacled Jewish pharmacist and recurring comic relief character on the animated television series Family Guy.
-
B.
Frank Goldberg
Frank Goldberg is a businessman best known for owning the former American Basketball Association team the San Diego Sails.
-
C.
William Goldenberg
William Goldenberg is an American film editor known for his work on numerous acclaimed movies, including several collaborations with directors like Michael Mann and Ben Affleck.
-
D.
Art Goldberg
Art Goldberg was a prominent activist and organizer associated with the 1960s Free Speech Movement at the University of California, Berkeley.
-
E.
Johnny Goldstein
Johnny Goldstein is an Israeli music producer and songwriter known for his work on international pop and hip-hop tracks.
- 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_69ad8588ba18819086a10951c32ecb80 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada6e67e948190afbd9cc6a3ade415 |
completed | March 8, 2026, 4:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b51c5ab7988190882df3b8198ad88a |
completed | March 14, 2026, 8:29 a.m. |
Created at: March 8, 2026, 3:07 p.m.