Triple
T23221844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shō Tai |
E580914
|
entity |
| Predicate | nobleTitleInJapan |
P66666
|
FINISHED |
| Object | marquis |
—
|
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: marquis | Statement: [Shō Tai, nobleTitleInJapan, marquis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nobleTitleInJapan Context triple: [Shō Tai, nobleTitleInJapan, marquis]
-
A.
nobleTitleElevated
Indicates that an entity’s noble rank or title has been raised to a higher level of nobility.
-
B.
nobleTitleOrStatus
Indicates that one entity holds, claims, or is associated with a particular noble rank, title, or social status in relation to another entity.
-
C.
nobleTitleFrom
Indicates that a person derives or holds their noble title from a specified source, such as a place, lineage, or authority.
-
D.
officeHolderTitleInJapanese
Indicates the official title or designation of an office holder as expressed in the Japanese language.
-
E.
aristocraticTitleIn
chosen
Indicates that an entity holds or is associated with a specific aristocratic or noble title within a particular jurisdiction or context.
- 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_69e2460389408190be74f41d217799a9 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1922924308190a26b00e09ce60ecd |
completed | April 29, 2026, 5:07 a.m. |
| PD | Predicate disambiguation | batch_69effcccee508190a7ae311fdd319806 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:08 p.m.