Triple
T10773340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grothendieck duality |
E254134
|
entity |
| Predicate | developedIn |
P283
|
FINISHED |
| Object | SGA |
E254121
|
NE 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: SGA | Statement: [Grothendieck duality, developedIn, SGA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SGA Context triple: [Grothendieck duality, developedIn, SGA]
-
A.
SGA
chosen
SGA is a monumental multi-volume seminar series on algebraic geometry, led by Alexander Grothendieck, that profoundly reshaped the foundations and methods of the field.
-
B.
SGA
SGA is the acronym commonly used to refer to the Secretariat-General for Administration, a central administrative body within a governmental or institutional structure.
-
C.
SGA 4½
SGA 4½ is a supplementary volume to Grothendieck’s Séminaire de Géométrie Algébrique that develops additional cohomological and topos-theoretic tools bridging SGA 4 and SGA 5.
-
D.
SG
SG is the vehicle registration code used on license plates for the Swiss canton of St. Gallen.
-
E.
SG
SG is the vehicle registration code used on license plates for Spain’s Segovia Province.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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. |
| NED1 | Entity disambiguation (via context triple) | batch_69de84b88ba08190afddea2976d12465 |
completed | April 14, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:16 p.m.