Triple
T297848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Musée Mécanique |
E6131
|
entity |
| Predicate | collectionOrigin |
P10914
|
FINISHED |
| Object | private collection of Edward Galland Zelinsky |
—
|
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: private collection of Edward Galland Zelinsky | Statement: [Musée Mécanique, collectionOrigin, private collection of Edward Galland Zelinsky]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collectionOrigin Context triple: [Musée Mécanique, collectionOrigin, private collection of Edward Galland Zelinsky]
-
A.
collectedThrough
Indicates that something was obtained, gathered, or acquired by means of a specified process, method, or channel.
-
B.
collectsFrom
Indicates that one entity gathers, receives, or takes something (such as items, data, or payments) from another entity.
-
C.
knownFrom
Indicates that one entity is aware of, has learned about, or recognizes another entity through a specified source, context, or medium.
-
D.
countryOfOrigin
Indicates the country from which an entity originally comes or was first produced, created, or established.
-
E.
committeeOfOrigin
Indicates the committee in which a proposal, bill, or item was first introduced or initially considered.
- F. None of above. chosen
Provenance (4 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_69a2e79114b081909490b3bf5a5dbb51 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2ea4778cc8190be7b648a82542891 |
completed | Feb. 28, 2026, 1:14 p.m. |
| PD | Predicate disambiguation | batch_69a2e937af888190a0960708f09ae033 |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2ea4545608190898436c72e10f39d |
completed | Feb. 28, 2026, 1:14 p.m. |
Created at: Feb. 28, 2026, 1:06 p.m.