Triple
T3819635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buddy Holly |
E84341
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Holley |
E223165
|
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: Holley | Statement: [Buddy Holly, familyName, Holley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Holley Context triple: [Buddy Holly, familyName, Holley]
-
A.
Holley
chosen
Holley is a surname most notably associated with Alexander Lyman Holley, a prominent 19th-century American engineer and steel industry pioneer.
-
B.
Tillotson
Tillotson is an English surname most notably associated with John Tillotson, a 17th-century Archbishop of Canterbury.
-
C.
Busch
Busch is a common German surname borne by numerous notable individuals across fields such as politics, the arts, and industry.
-
D.
Hendrick
Hendrick is a Dutch given name historically borne by figures such as the 17th-century painter Hendrick Cornelisz. van Vliet.
-
E.
Perkins
Perkins is a common English surname borne by numerous notable individuals across politics, arts, sports, and academia.
- 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_69aed931f5908190be2c07af66d4df25 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeea601d408190b09dc486e77488d4 |
completed | March 9, 2026, 3:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4fb466a108190ac203ee00ce58f04 |
completed | March 14, 2026, 6:08 a.m. |
Created at: March 9, 2026, 3:17 p.m.