Triple
T26371305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hunan Provincial Museum |
E660779
|
entity |
| Predicate | mainSubjectOfCollection |
P106967
|
FINISHED |
| Object | history of Hunan Province |
—
|
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: history of Hunan Province | Statement: [Hunan Provincial Museum, mainSubjectOfCollection, history of Hunan Province]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainSubjectOfCollection Context triple: [Hunan Provincial Museum, mainSubjectOfCollection, history of Hunan Province]
-
A.
subjectOfCatalog
Indicates that something is the primary focus or entry described within a catalog or cataloging record.
-
B.
hasCollectionSubject
chosen
Indicates that a collection is about or thematically centered on a particular subject.
-
C.
primaryCollectionOf
Indicates that one entity serves as the main or principal collection to which another entity primarily belongs or is associated.
-
D.
subjectOfIntroduction
Indicates that one entity is the topic or focus being introduced by another entity.
-
E.
titleSubjectOf
Indicates that a title (such as a book, article, or work) is about or primarily concerns a particular subject.
- 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_69ee812a698881908d6a58265995fa39 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f6383625cc8190aa223d8ef655743c |
completed | May 2, 2026, 5:45 p.m. |
| PD | Predicate disambiguation | batch_69f63709e4848190b5cf322e06b23fb6 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 26, 2026, 10:58 p.m.