Triple
T8087312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Al Golden |
E188765
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Al Golden |
E188765
|
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: Al Golden | Statement: [Al Golden, name, Al Golden]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Al Golden Context triple: [Al Golden, name, Al Golden]
-
A.
Al Golden
chosen
Al Golden is an American football coach best known for revitalizing the Temple University football program and later serving as head coach at the University of Miami.
-
B.
Jeremy Gold
Jeremy Gold is a television producer and executive known for his work on the AMC Western drama series "Hell on Wheels."
-
C.
Alvin Sargent
Alvin Sargent was an American screenwriter best known for his Oscar-winning work on films like "Julia" and "Ordinary People" and for co-writing several "Spider-Man" movies.
-
D.
Bill Lamar
Bill Lamar is a notable individual who shares the Lamar surname and has achieved sufficient prominence to be specifically recognized by name.
-
E.
Holter Graham
Holter Graham is an American actor and audiobook narrator known for voicing numerous popular titles across fiction and non-fiction.
- 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_69ca82b662e88190b9323daab8c28a21 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4162244481908ab1202a9974deaa |
completed | March 31, 2026, 3:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc6406395c8190ad8db69c878ce9b8 |
completed | April 1, 2026, 12:17 a.m. |
Created at: March 30, 2026, 5:29 p.m.