Triple
T3568720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kobo Daishi |
E75515
|
entity |
| Predicate | posthumousTitleYear |
P50593
|
FINISHED |
| Object | 921 |
—
|
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: 921 | Statement: [Kobo Daishi, posthumousTitleYear, 921]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: posthumousTitleYear Context triple: [Kobo Daishi, posthumousTitleYear, 921]
-
A.
posthumousAwardsRestoredInYear
Indicates that awards, previously revoked or unrecognized during a person’s lifetime, were officially reinstated or granted in a specified year after their death.
-
B.
royalDesignationYear
Indicates the year in which an entity was formally granted or recognized with a royal status or designation.
-
C.
successorTitle
Indicates the title or position that directly follows and replaces a previous one in a sequence or succession.
-
D.
isPosthumous
Indicates that something occurs, is created, or is conferred after the death of the person to whom it relates.
-
E.
titleAfterAbdication
Indicates the formal title or designation a person holds after they have abdicated a previous position of authority or rank.
- 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_69ad85d512708190829c8b2d3a2ccfb8 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0c083ac8190a71cd9ede2114cac |
completed | March 8, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69adb8364d848190a96a9bc7a6126af2 |
completed | March 8, 2026, 5:56 p.m. |
| PDg | Predicate description generation | batch_69adba25c66c81909a05a97327828c41 |
completed | March 8, 2026, 6:04 p.m. |
Created at: March 8, 2026, 3:21 p.m.