Triple
T27343435
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Discovery (OV-103) |
E684169
|
entity |
| Predicate | displayMuseum |
P3831
|
FINISHED |
| Object | Smithsonian National Air and Space 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: Smithsonian National Air and Space Museum | Statement: [Discovery (OV-103), displayMuseum, Smithsonian National Air and Space Museum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: displayMuseum Context triple: [Discovery (OV-103), displayMuseum, Smithsonian National Air and Space Museum]
-
A.
museumDisplayType
Indicates the manner or format in which items are presented or exhibited within a museum setting.
-
B.
museumHolds
Indicates that a museum possesses, preserves, or has custody of a particular item or collection within its holdings.
-
C.
orientationInMuseum
Indicates the spatial positioning or directional arrangement of an object or exhibit within a museum space.
-
D.
museumAt
chosen
Indicates that an entity (such as an exhibit, artifact, or event) is located at or associated with a particular museum.
-
E.
museumSection
Indicates that one entity is a section, area, or subdivision within a museum associated with the other entity.
- 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_69ef1480a76481908684256ddd5bfda3 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f62ba0fedc8190b63a546f7d893676 |
completed | May 2, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69f620e4b1c88190a17940251abc68fd |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:44 a.m.