Triple
T38157293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Masako Ichijō |
E952919
|
entity |
| Predicate | titleAfterHusbandDeath |
P105828
|
FINISHED |
| Object | Empress Dowager Shōken |
—
|
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: Empress Dowager Shōken | Statement: [Masako Ichijō, titleAfterHusbandDeath, Empress Dowager Shōken]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleAfterHusbandDeath Context triple: [Masako Ichijō, titleAfterHusbandDeath, Empress Dowager Shōken]
-
A.
titleAfterSpouseAccession
chosen
Indicates that an entity holds or adopts a particular title only after their spouse has acceded to a specified position or rank.
-
B.
styleAfterHusbandDeath
Indicates that an entity adopts or changes its style in response to, or following, the death of its husband.
-
C.
titleAfterDivorce
Indicates the formal title or style a person holds or uses following a divorce.
-
D.
titleAfterSecondMarriage
Indicates the title or designation a person holds specifically after entering into their second marriage.
-
E.
afterHusbandDeathRole
Indicates the role or status a person assumes after the death of their husband.
- 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_69f76f0b93c48190a117319ab3a9f282 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a00144238708190acbec3f791cc873e |
completed | May 10, 2026, 5:14 a.m. |
| PD | Predicate disambiguation | batch_6a00120244a4819090ef39070aba9d99 |
completed | May 10, 2026, 5:05 a.m. |
Created at: May 3, 2026, 4:21 p.m.