Triple
T22534578
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | One More Light |
E557122
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Francis White |
—
|
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: Francis White | Statement: [One More Light, producer, Francis White]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Francis White Context triple: [One More Light, producer, Francis White]
-
A.
Francis White
chosen
Francis White is a songwriter best known for co-writing Florence + the Machine’s track “What the Water Gave Me.”
-
B.
Joseph White
Joseph White is a cinematographer known for his work on the cult rock opera horror film "Repo! The Genetic Opera."
-
C.
William Thomas Goode
William Thomas Goode was a British academic, linguist, and journalist known for his early 20th-century writings and reporting, particularly on international affairs.
-
D.
Ennis C. Whitehead
Ennis C. Whitehead was a U.S. Air Force general and World War II air commander known for his leadership in the Southwest Pacific theater.
-
E.
William Whitaker
William Whitaker was a prominent British geologist and hydrogeologist known for his pioneering work on the geology and groundwater resources of England and Wales.
- 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_69e11e57483c8190b0887c4f8ff26446 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ed952f48190b63225e7de131679 |
completed | April 29, 2026, 1:28 a.m. |
Created at: April 16, 2026, 8:51 p.m.