Triple
T5179013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Empress Dowager of Japan |
E116869
|
entity |
| Predicate | hasPrecondition |
P14814
|
FINISHED |
| Object | death of reigning emperor husband |
—
|
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: death of reigning emperor husband | Statement: [Empress Dowager of Japan, hasPrecondition, death of reigning emperor husband]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrecondition Context triple: [Empress Dowager of Japan, hasPrecondition, death of reigning emperor husband]
-
A.
hasPrecedingCondition
Indicates that one condition occurs or exists before another condition in time or sequence.
-
B.
hasCondition
Indicates that an entity possesses, experiences, or is affected by a particular condition or state.
-
C.
precondition
chosen
Indicates that one event, state, or condition must be true or occur before another event, state, or condition can validly or successfully take place.
-
D.
hasPrecedence
Indicates that one entity occurs, is considered, or is applied before another in order, priority, or importance.
-
E.
hasPrecedingWork
Indicates that one work comes before another in a sequence, serving as its predecessor.
- 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_69bd446140f08190becb93c61158f27f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd79978a208190b2e5909795108327 |
completed | March 20, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69bd77b529948190b86671ebe43f4734 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:45 p.m.