Triple
T25005885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Door |
E625839
|
entity |
| Predicate | roleInNeverwhere |
P164770
|
FINISHED |
| Object | central figure |
—
|
LITERAL 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: central figure | Statement: [Door, roleInNeverwhere, central figure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInNeverwhere Context triple: [Door, roleInNeverwhere, central figure]
-
A.
roleInDarkCity
Indicates that an entity has a specific role, function, or character within the context of the work "Dark City."
-
B.
roleInWatchmen
Indicates that one entity has a specific role or function within the context of the work "Watchmen" in relation to the other entity.
-
C.
roleInKnightfall
Indicates that an entity has a specific role or participation in the context of "Knightfall" (such as a project, event, or production) in relation to another entity.
-
D.
roleInDishonored
Indicates that an entity holds or plays a particular role within the context of the work titled "Dishonored."
-
E.
roleInMysteryMen
Indicates that one entity has a specific role or part in the context of "Mystery Men," such as in its story, production, or related work.
- F. None of above. chosen
Provenance (4 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_69e2ff26c50481908bc82e799c9e6587 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f650fc44e48190bc0e0a935eac62a6 |
completed | May 2, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69f64cab1f648190a2a9460690d18a37 |
completed | May 2, 2026, 7:12 p.m. |
| PDg | Predicate description generation | batch_69f650c466b881908954e43bfebae8a4 |
completed | May 2, 2026, 7:30 p.m. |
Created at: April 18, 2026, 6:05 a.m.