Triple
T8369005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maison Centrale |
E197405
|
entity |
| Predicate | remainingPortion |
P47939
|
FINISHED |
| Object | museum |
—
|
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: museum | Statement: [Maison Centrale, remainingPortion, museum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: remainingPortion Context triple: [Maison Centrale, remainingPortion, museum]
-
A.
reconstructedPortion
Indicates that a portion of an object, structure, or data has been rebuilt or restored from partial, damaged, or missing original information.
-
B.
handlesPortionOf
Indicates that one entity is responsible for managing or dealing with a specific part or subset of another entity or task.
-
C.
containsPortionOf
Indicates that one entity includes or holds a part, segment, or fraction of another entity.
-
D.
survivingPortions
chosen
Indicates that certain parts or segments of something remain intact or extant after other portions have been lost, destroyed, or removed.
-
E.
hasMissingPortions
Indicates that an entity is incomplete because some of its expected parts or sections are absent.
- 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_69ca82f56730819080cec5d991c76f4c |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb808f7c0481909fef5834cb6e7a3e |
completed | March 31, 2026, 8:06 a.m. |
| PD | Predicate disambiguation | batch_69cb70cd04b08190ab5f72afd22a7967 |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6:01 p.m.