Triple
T6360720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British earldoms |
E143099
|
entity |
| Predicate | mayBeSubsidiaryTitleOf |
P1916
|
FINISHED |
| Object | duke |
—
|
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: duke | Statement: [British earldoms, mayBeSubsidiaryTitleOf, duke]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayBeSubsidiaryTitleOf Context triple: [British earldoms, mayBeSubsidiaryTitleOf, duke]
-
A.
hasSubsidiaryTitle
chosen
Indicates that an entity has an additional or secondary title formally associated with its main title.
-
B.
mayBeTitled
Indicates that an entity can optionally bear or be assigned a particular title, but is not required to have it.
-
C.
hasSubsidiaryLabel
Indicates that one entity is identified as a subsidiary or subordinate organization of another entity.
-
D.
inheritsTitle
Indicates that one entity receives and assumes a formal title or rank previously held by another entity, typically through succession or inheritance.
-
E.
isTitleSeriesOf
Indicates that one entity is the title or name associated with a particular series (such as a book, film, or media franchise).
- 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_69c008d7a9c4819098d647ec47776917 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c067fa0d0c819098d01545849142fc |
completed | March 22, 2026, 10:06 p.m. |
| PD | Predicate disambiguation | batch_69c060ec091c8190912aac44e1b8b1c9 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:32 p.m.