Triple
T8936571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sharon Gebenini |
E212791
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | John Holmes |
E347996
|
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: John Holmes | Statement: [Sharon Gebenini, spouse, John Holmes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Holmes Context triple: [Sharon Gebenini, spouse, John Holmes]
-
A.
John Holmes
chosen
John Holmes was an American poet and influential creative writing teacher known for mentoring notable poets, including Anne Sexton, at Tufts University.
-
B.
John Holmes
John Holmes was a famous American adult film actor of the 1970s and early 1980s, widely known for his prolific career and distinctive physical attributes.
-
C.
Gabriel Harris
Gabriel Harris is an American percussionist and musician best known for his work with his mother, folk singer and activist Joan Baez, as well as other world and folk music artists.
-
D.
William Holmes
William Holmes was a film editor best known for his Academy Award-winning work on the 1941 biographical war film "Sergeant York."
-
E.
Gary Starkweather
Gary Starkweather was an American engineer and inventor best known for creating the laser printer while working at Xerox.
- 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_69ca839694c88190b324ffeb43d23b08 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66b3628881909544507628980c25 |
completed | April 1, 2026, 12:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfd095a07c81908e164cfa68fb693e |
completed | April 3, 2026, 2:37 p.m. |
Created at: March 30, 2026, 6:58 p.m.