Triple
T10773015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Éléments de géométrie algébrique |
E254127
|
entity |
| Predicate | EGA III topic |
P62307
|
FINISHED |
| Object | cohomologie des faisceaux cohérents |
—
|
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: cohomologie des faisceaux cohérents | Statement: [Éléments de géométrie algébrique, EGA III topic, cohomologie des faisceaux cohérents]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: EGA III topic Context triple: [Éléments de géométrie algébrique, EGA III topic, cohomologie des faisceaux cohérents]
-
A.
thirdGeneration
Indicates that one entity is the grandchild (third generation) relative to another entity in a lineage or succession.
-
B.
governedTopic
Indicates that a governing entity exercises authority, control, or regulatory oversight over a particular topic, issue, or domain.
-
C.
season3Subject
Indicates that the subject is associated with or pertains to the third season of a series or recurring event.
-
D.
thirdElement
chosen
Indicates that one entity is the third element in an ordered sequence or tuple associated with another entity.
-
E.
legacyTopic
Indicates that a topic or subject is considered outdated, superseded, or retained only for backward compatibility or historical reasons.
- 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_69d6aa5f54f4819082d0bbcb6f8797e6 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d7329b27748190bd0e2569c7972fd1 |
completed | April 9, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69d6f31455648190b5c24690487b1b54 |
completed | April 9, 2026, 12:30 a.m. |
Created at: April 8, 2026, 9:16 p.m.