Triple
T11086032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grothendieck–Ogg–Shafarevich formula |
E262121
|
entity |
| Predicate | hasCodomain |
P7031
|
FINISHED |
| Object | integers (Euler characteristic values) |
—
|
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: integers (Euler characteristic values) | Statement: [Grothendieck–Ogg–Shafarevich formula, hasCodomain, integers (Euler characteristic values)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCodomain Context triple: [Grothendieck–Ogg–Shafarevich formula, hasCodomain, integers (Euler characteristic values)]
-
A.
codomain
chosen
Indicates the set of all possible output values that a function or mapping can produce, regardless of which values are actually attained.
-
B.
hasCodaTypes
Indicates that a linguistic unit (such as a syllable) possesses one or more specific types of codas in its structure.
-
C.
hasCoda
Indicates that an entity (such as a word, syllable, or musical piece) possesses a coda, i.e., a concluding segment or closing element.
-
D.
hasCanonicalMapFrom
Indicates that there exists a standard or uniquely determined structure-preserving map from one entity to another.
-
E.
hasCodeIn
Indicates that one entity is represented, defined, or implemented within the codebase or coding context of another entity.
- 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_69d6aa9983c08190b0ef61603b69feac |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d799c3ed9c8190a3f5cdf1fe0e74a2 |
completed | April 9, 2026, 12:21 p.m. |
| PD | Predicate disambiguation | batch_69d744185a5881909ba4cf151d1798ec |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:27 p.m.