Triple
T2122797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Department of Near Eastern Antiquities |
E43962
|
entity |
| Predicate | museumFunction |
P18644
|
FINISHED |
| Object | conservation of artifacts |
—
|
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: conservation of artifacts | Statement: [Department of Near Eastern Antiquities, museumFunction, conservation of artifacts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: museumFunction Context triple: [Department of Near Eastern Antiquities, museumFunction, conservation of artifacts]
-
A.
operatesMuseum
Indicates that one entity manages and runs the day-to-day operations of a museum.
-
B.
museumAt
Indicates that an entity (such as an exhibit, artifact, or event) is located at or associated with a particular museum.
-
C.
museumHolds
Indicates that a museum possesses, preserves, or has custody of a particular item or collection within its holdings.
-
D.
museumFocus
chosen
Indicates that a museum is primarily dedicated to or specializes in a particular subject, theme, or type of collection.
-
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_69a88717cfe48190b7ecdd68c824848a |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abbb5445848190bbc6dc1236e9f749 |
completed | March 7, 2026, 5:44 a.m. |
| PD | Predicate disambiguation | batch_69abb7bd86cc8190938ef06c1ed6d969 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:44 p.m.