Triple
T8870498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sara Sothern |
E211140
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Howard Taylor |
E802769
|
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: Howard Taylor | Statement: [Sara Sothern, relative, Howard Taylor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Howard Taylor Context triple: [Sara Sothern, relative, Howard Taylor]
-
A.
Howard Taylor
chosen
Howard Taylor was an American actor and film producer best known as the brother of iconic actress Elizabeth Taylor.
-
B.
George Washington Taylor
George Washington Taylor was an American merchant best known for co-founding the historic department store chain Lord & Taylor.
-
C.
Harold Briggs
Harold Briggs was a British Army officer best known for devising and implementing the Briggs Plan to combat communist insurgency during the Malayan Emergency.
-
D.
J.H. Taylor
J.H. Taylor was a pioneering English professional golfer and multiple Open Championship winner who helped shape the early development of modern golf.
-
E.
William Dewhurst
William Dewhurst was an actor known for his role in the early 20th-century film "Sabotage."
- 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_69ca838d3c7c8190a849566d5afd2b11 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6126d2f88190979ab25772ee657c |
completed | April 1, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d190b5bb70819082b8eeb18bd5f1f6 |
completed | April 4, 2026, 10:29 p.m. |
Created at: March 30, 2026, 6:51 p.m.