Triple
T36191920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kin'yō Wakashū |
E1047012
|
entity |
| Predicate | compilerAlternativeName |
P19945
|
FINISHED |
| Object | Minamoto no Toshiyori |
—
|
NE NERFINISHED |
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: Minamoto no Toshiyori | Statement: [Kin'yō Wakashū, compilerAlternativeName, Minamoto no Toshiyori]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: compilerAlternativeName Context triple: [Kin'yō Wakashū, compilerAlternativeName, Minamoto no Toshiyori]
-
A.
compilerFamily
Indicates that one compiler belongs to, or is categorized under, a particular family or lineage of related compilers.
-
B.
compilerOrEditor
Indicates that one entity functions as a compiler or editor of the other entity, typically preparing, organizing, or revising its content.
-
C.
compilerType
Indicates the specific kind or category of compiler associated with or used by an entity.
-
D.
compilerLanguage
Indicates that one entity is the programming language in which a given compiler is implemented.
-
E.
compilerPseudonymUsedBy
chosen
Indicates that a particular pseudonym is used as an alternate name or alias by a specific compiler.
- 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_69f76e3d4fbc81908c159c7beeb4ce00 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7ba6d06f48190a71b5a2f19e2232f |
completed | May 3, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a4aad48190a62e41c5e39339d9 |
completed | May 3, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:08 p.m.