Triple
T10732851
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Serre’s conjecture on Galois representations |
E253116
|
entity |
| Predicate | proofCompletedInYear |
P27180
|
FINISHED |
| Object | 2008 |
—
|
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: 2008 | Statement: [Serre’s conjecture on Galois representations, proofCompletedInYear, 2008]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: proofCompletedInYear Context triple: [Serre’s conjecture on Galois representations, proofCompletedInYear, 2008]
-
A.
workCompletionYear
Indicates the calendar year in which a particular work, project, or task was completed.
-
B.
originalCompletionYear
Indicates the year in which something (such as a project, work, or construction) was first fully completed.
-
C.
hasFirstProofYear
chosen
Indicates the year in which something was first proven or formally demonstrated to be true.
-
D.
confirmationYear
Indicates the calendar year in which a confirmation event or formal validation of something took place.
-
E.
claimedYear
Indicates the year that is asserted or reported as being associated with an event, status, or fact, regardless of whether it is verified.
- 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_69d6aa5d8be481909a43218b2bfdbe95 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d7101ff9808190a27fcc06da097ea3 |
completed | April 9, 2026, 2:34 a.m. |
| PD | Predicate disambiguation | batch_69d6f309a44881908e49e3ba478c35b4 |
completed | April 9, 2026, 12:30 a.m. |
Created at: April 8, 2026, 9:14 p.m.