Triple
T23432762
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anya |
E563376
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Gary Goldman |
E566894
|
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: Gary Goldman | Statement: [Anya, creator, Gary Goldman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gary Goldman Context triple: [Anya, creator, Gary Goldman]
-
A.
Gary Goldman
Gary Goldman is an American screenwriter best known for his work on major science fiction and action films, including the 1990 movie "Total Recall."
-
B.
Gary Goldman
chosen
Gary Goldman is an American animator, director, and producer best known for his work on Don Bluth–style animated films such as Anastasia.
-
C.
David Goldman
David Goldman was a British entrepreneur best known for co-founding the accounting software company Sage Group and helping to build it into a global business.
-
D.
Andrew Goldman
Andrew Goldman is a film editor known for his work on the independent feature "Tiny Furniture."
-
E.
Len Goldstein
Len Goldstein is a television producer known for his executive production work on series such as "The Astronaut Wives Club."
- 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_69e24553980c8190bb66a2ae0bdab125 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1a5d920548190904f80c7c40cba06 |
completed | April 29, 2026, 6:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c67af2b4081909384d5967cf2672a |
completed | May 19, 2026, 1:37 p.m. |
Created at: April 17, 2026, 5:49 p.m.