Triple
T13509425
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ky Fan’s lemma |
E321096
|
entity |
| Predicate | typeOfConclusion |
P57345
|
FINISHED |
| Object | existence theorem |
—
|
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: existence theorem | Statement: [Ky Fan’s lemma, typeOfConclusion, existence theorem]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfConclusion Context triple: [Ky Fan’s lemma, typeOfConclusion, existence theorem]
-
A.
conclusionType
chosen
Indicates the specific kind or category of conclusion associated with an argument, inference, or reasoning process.
-
B.
typicalConclusion
Indicates that one entity is the usual or expected outcome, result, or ending that follows from another entity or situation.
-
C.
concludedThat
Indicates that one entity has reached or stated a judgment, inference, or decision about a proposition or situation involving another entity.
-
D.
outcomeType
Indicates the specific category or nature of the result produced by an event, process, or action.
-
E.
concludesAbout
Indicates that one entity forms or states a conclusion regarding another entity or its properties.
- 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_69d807629d6c8190998f1b9bb12d2ed0 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbaf85a74081909eb08751fc55ce8f |
completed | April 12, 2026, 2:43 p.m. |
| PD | Predicate disambiguation | batch_69dbae0b63748190b5e207f84b2532ea |
completed | April 12, 2026, 2:36 p.m. |
Created at: April 9, 2026, 9:43 p.m.