Triple
T31279576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kōji |
E797622
|
entity |
| Predicate | hasSecondMora |
P198598
|
FINISHED |
| Object | う (u, lengthening o) |
—
|
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: う (u, lengthening o) | Statement: [Kōji, hasSecondMora, う (u, lengthening o)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSecondMora Context triple: [Kōji, hasSecondMora, う (u, lengthening o)]
-
A.
hasSecond
Indicates that one entity is the second item, position, or element in an ordered sequence or pair relative to another entity.
-
B.
hasSecondPartForm
Indicates that an entity is composed of a second component whose form or structure is specified by the related entity.
-
C.
hasSecondKindForm
Indicates that an entity is associated with a secondary or alternative form or representation distinct from its primary form.
-
D.
secondSyllable
Indicates that the second syllable of one linguistic unit corresponds to, matches, or is identified as a particular syllable or sound in relation to another entity.
-
E.
secondSyllableTone
Indicates that the relationship specifies the tonal value or pitch pattern of the second syllable in a word or utterance.
- 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_69f224def9088190a37034eab3daf57f |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fef5cf8da881908260ec633830375d |
completed | May 9, 2026, 8:52 a.m. |
| PD | Predicate disambiguation | batch_69fef455e40481909861c82007b79bc0 |
completed | May 9, 2026, 8:46 a.m. |
| PDg | Predicate description generation | batch_69fef5cec8208190b85665ab6a511a08 |
completed | May 9, 2026, 8:52 a.m. |
Created at: April 29, 2026, 9:13 p.m.