Triple
T5570524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fermat's Last Theorem |
E146188
|
entity |
| Predicate | correctedProofPublicationYear |
P64860
|
FINISHED |
| Object | 1995 |
—
|
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: 1995 | Statement: [Fermat's Last Theorem, correctedProofPublicationYear, 1995]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: correctedProofPublicationYear Context triple: [Fermat's Last Theorem, correctedProofPublicationYear, 1995]
-
A.
publicationYear
Indicates the specific calendar year in which a work was formally published or released.
-
B.
lastPublicationYear
Indicates the year in which an entity’s most recent publication was released.
-
C.
involvesPublication
Indicates that an action, event, or process includes or is associated with a specific publication as a relevant component.
-
D.
yearOfPublicDisclosure
Indicates the calendar year in which information, an invention, or other subject matter was first publicly disclosed.
-
E.
formerPublication
Indicates that an entity was previously published in, or associated as a publication with, another entity but is no longer currently so.
- 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_69c008ffed108190a084602227af6157 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c020502a288190af37f9ebb88fccae |
completed | March 22, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69c01b12826c8190969a584d0f53aa44 |
completed | March 22, 2026, 4:38 p.m. |
| PDg | Predicate description generation | batch_69c01f4032408190a4f0d2eb21ebd870 |
completed | March 22, 2026, 4:56 p.m. |
Created at: March 22, 2026, 3:37 p.m.