Triple
T37349144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winter Gardens (Sunderland) |
E927268
|
entity |
| Predicate | isPartOfMuseumComplex |
P112021
|
FINISHED |
| Object | Sunderland Museum |
—
|
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: Sunderland Museum | Statement: [Winter Gardens (Sunderland), isPartOfMuseumComplex, Sunderland Museum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPartOfMuseumComplex Context triple: [Winter Gardens (Sunderland), isPartOfMuseumComplex, Sunderland Museum]
-
A.
hasMuseumAt
Indicates that a museum is located at or exists in a specified place or location.
-
B.
housedWithinComplex
chosen
Indicates that one entity is located inside and functionally part of a larger building or facility complex.
-
C.
hasMuseumComponent
Indicates that something includes, contains, or is composed of a museum or museum-related part as one of its components.
-
D.
isLargestMultipurposeMuseumIn
Indicates that a museum is the largest multipurpose museum within a specified geographic area or location.
-
E.
museumAt
Indicates that an entity (such as an exhibit, artifact, or event) is located at or associated with a particular museum.
- 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_69f76eb5e034819088e53ab5b7909a68 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a000be59ad88190a6aa3a42c097796d |
completed | May 10, 2026, 4:39 a.m. |
| PD | Predicate disambiguation | batch_6a000ab6e9bc81908300b81d004e5921 |
completed | May 10, 2026, 4:33 a.m. |
Created at: May 3, 2026, 4:16 p.m.