Triple
T17152122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 牛島満 |
E416245
|
entity |
| Predicate | 家系・出自 |
P126313
|
FINISHED |
| Object | 鹿児島の士族出身 |
—
|
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: 鹿児島の士族出身 | Statement: [牛島満, 家系・出自, 鹿児島の士族出身]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 家系・出自 Context triple: [牛島満, 家系・出自, 鹿児島の士族出身]
-
A.
thoroughbredFamily
Indicates that one entity belongs to, or is classified within, a specific Thoroughbred horse family lineage associated with the other entity.
-
B.
familyNameDerivedFrom
Indicates that one entity’s family name originates from, or is etymologically derived from, another entity.
-
C.
breedingFamily
Indicates that one entity belongs to or is part of the family group used for breeding or reproduction with the other entity.
-
D.
sourceOfLineageFor
Indicates that one entity serves as the origin or ancestral source from which another entity’s lineage is derived.
-
E.
houseOfOrigin
Indicates the original location, institution, or context from which an entity first came or was initially produced.
- 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_69d886d279c081909f8ff1f743ddeb69 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f40861e08190bad1a3ec87691132 |
completed | April 18, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69e3830d2a90819092386717dc56f0e8 |
completed | April 18, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69e3873f62108190966c4e741ebd548d |
completed | April 18, 2026, 1:29 p.m. |
Created at: April 10, 2026, 5:36 a.m.