Triple
T8888536
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Art Farmer |
E211596
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Addison Farmer |
E768154
|
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: Addison Farmer | Statement: [Art Farmer, sibling, Addison Farmer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Addison Farmer Context triple: [Art Farmer, sibling, Addison Farmer]
-
A.
Addison Farmer
chosen
Addison Farmer was an American jazz double bassist known for his work in the 1950s and 1960s, including collaborations with prominent bebop and hard bop musicians.
-
B.
Addison Clark
Addison Clark was an American educator and co-founder of Texas Christian University, playing a key role in its early development and leadership.
-
C.
Madison Epps
Madison Epps is a daughter of American stand-up comedian and actor Mike Epps.
-
D.
Morgan Woodward
Morgan Woodward was an American character actor best known for his numerous guest roles on classic television series such as "Gunsmoke," "Dallas," and "Star Trek."
-
E.
Reilly Wright
Reilly Wright is one of the children of Hall of Fame college basketball coach Jay Wright.
- 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_69ca83907954819096d52a245b635841 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc618e58d08190be3ebcbe3701b1db |
completed | April 1, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc92e668c819086e694f92c04add6 |
completed | April 3, 2026, 2:05 p.m. |
Created at: March 30, 2026, 6:53 p.m.