Triple
T18543945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thinktank, Birmingham Science Museum |
E453173
|
entity |
| Predicate | hasGalleryTheme |
P62774
|
FINISHED |
| Object | engineering |
—
|
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: engineering | Statement: [Thinktank, Birmingham Science Museum, hasGalleryTheme, engineering]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGalleryTheme Context triple: [Thinktank, Birmingham Science Museum, hasGalleryTheme, engineering]
-
A.
hasGallery
Indicates that one entity possesses, contains, or is associated with a gallery, such as a collection or display space.
-
B.
hasGalleryLocation
Indicates that an entity is associated with a specific gallery location where it is displayed, stored, or made accessible.
-
C.
hasViewingGallery
Indicates that one entity includes or provides a designated area from which another entity can be observed or viewed.
-
D.
hasThemeType
chosen
Indicates that something is associated with or characterized by a particular thematic category or type.
-
E.
hasThemeConnection
Indicates a relationship where one entity is linked to another through a shared or related theme, topic, or conceptual focus.
- 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_69d8d388b0c881908e610a1c45b52640 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e534b935c48190a34b17eeae4fd583 |
completed | April 19, 2026, 8:02 p.m. |
| PD | Predicate disambiguation | batch_69e469e274a48190a570b25cfef4d890 |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:38 a.m.