Triple
T21483338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Hentschel |
E530052
|
entity |
| Predicate | workedWith |
P398
|
FINISHED |
| Object | Harry Nilsson |
—
|
NE NERFINISHED |
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: Harry Nilsson | Statement: [David Hentschel, workedWith, Harry Nilsson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Nilsson Context triple: [David Hentschel, workedWith, Harry Nilsson]
-
A.
Harry Nilsson
chosen
Harry Nilsson was an American singer-songwriter known for his exceptional vocal range and studio craftsmanship, celebrated for hits like "Without You" and "Everybody's Talkin'" and his close association with The Beatles.
-
B.
Jack Nitzsche
Jack Nitzsche was an American musician, arranger, and film composer known for his influential work in pop music and acclaimed movie scores.
-
C.
Art Garfunkel
Art Garfunkel is an American singer and actor best known as the soaring tenor half of the folk-rock duo Simon & Garfunkel.
-
D.
Kim Garfunkel
Kim Garfunkel is an American singer and actress best known as the wife and frequent musical collaborator of Art Garfunkel.
-
E.
Peter Nilson
Peter Nilson was a Swedish astronomer and science fiction author known for his popular science writing and imaginative speculative novels.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea35945481909e5982429962de39 |
completed | April 23, 2026, 9:45 a.m. |
Created at: April 16, 2026, 6:21 p.m.