Triple
T24920456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Book of Dust |
E624106
|
entity |
| Predicate | mainProtagonistOfFirstVolume |
P115631
|
FINISHED |
| Object | Malcolm Polstead |
—
|
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: Malcolm Polstead | Statement: [The Book of Dust, mainProtagonistOfFirstVolume, Malcolm Polstead]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainProtagonistOfFirstVolume Context triple: [The Book of Dust, mainProtagonistOfFirstVolume, Malcolm Polstead]
-
A.
hasProtagonistInFirstVolume
chosen
Indicates that a work’s first volume features a specific entity as its main character.
-
B.
mainProtagonist
Indicates that the subject is the central character or primary focus in the narrative of the related work.
-
C.
protagonistIs
Indicates that one entity serves as the main character or central figure in relation to another entity or narrative context.
-
D.
hasProtagonist
Indicates that a work of narrative has a main character who serves as its central focus or driving agent.
-
E.
laterMainCharacterOf
Indicates that one entity becomes the main character of a work at a later point in time, succeeding another main character.
- F. None of above.
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_69e2fac889c081908e9ff686cb428e5a |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f44a417a58819081777e18dda149fd |
completed | May 1, 2026, 6:37 a.m. |
| PD | Predicate disambiguation | batch_69f442b8479c8190a7c8e416ac9e28a0 |
completed | May 1, 2026, 6:05 a.m. |
Created at: April 18, 2026, 5:28 a.m.