Triple
T1395162
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tennō Tanjōbi |
E30648
|
entity |
| Predicate | dateChangesWith |
P27702
|
FINISHED |
| Object | accession of a new emperor |
—
|
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: accession of a new emperor | Statement: [Tennō Tanjōbi, dateChangesWith, accession of a new emperor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateChangesWith Context triple: [Tennō Tanjōbi, dateChangesWith, accession of a new emperor]
-
A.
nameChangeDate
Indicates the date on which an entity’s name was officially changed.
-
B.
historicalOffsetChanges
Indicates that the relationship captures past changes in an offset value between entities, including when and how that offset was modified over time.
-
C.
movementDate
Indicates the date on which a movement, transfer, or relocation event occurs.
-
D.
dateObserved
Indicates the specific date on which an event, condition, or measurement was recorded or observed.
-
E.
dateSignificance
Indicates the specific importance, meaning, or notable role that a particular date holds within a given context or relationship.
- 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_69a498fd4e408190bd73eca30ea9754c |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c37e60388190a8efcb345be7a1b9 |
completed | March 1, 2026, 10:53 p.m. |
| PD | Predicate disambiguation | batch_69a4bf017f8081908572121560ec621f |
completed | March 1, 2026, 10:34 p.m. |
| PDg | Predicate description generation | batch_69a4c13270d8819081d8ee1be34cabf5 |
completed | March 1, 2026, 10:44 p.m. |
Created at: March 1, 2026, 7:59 p.m.