Triple
T17288667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Sixth Form |
E419723
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Tom Dolby |
E86556
|
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: Tom Dolby | Statement: [The Sixth Form, author, Tom Dolby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Dolby Context triple: [The Sixth Form, author, Tom Dolby]
-
A.
Tom Dolby
chosen
Tom Dolby is an American novelist and filmmaker known for works exploring themes of identity, privilege, and LGBTQ+ experience.
-
B.
Thomas Dolby
Thomas Dolby is an English musician, producer, and technology entrepreneur best known for his pioneering work in synth-pop and the hit song "She Blinded Me with Science."
-
C.
David Dolby
David Dolby is a member of the Dolby family, known as the son of Dagmar Dolby and the late audio technology pioneer Ray Dolby.
-
D.
Greg Phillinganes
Greg Phillinganes is an American keyboardist, musical director, and session musician renowned for his work with artists like Michael Jackson, Stevie Wonder, and Eric Clapton.
-
E.
Danny Rampling
Danny Rampling is a British DJ and producer widely recognized as a pioneering figure in the UK acid house movement and club culture.
- 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_69d886db32608190a61e18862c5a8af6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e43781b7808190a0528ee9c54a0c66 |
completed | April 19, 2026, 2:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a018c407fe8819095b16b171f29cf1b |
completed | May 11, 2026, 7:58 a.m. |
Created at: April 10, 2026, 5:40 a.m.