Triple
T27971521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Song Emperor Lizong |
E706368
|
entity |
| Predicate | successorStateThreat |
P151730
|
FINISHED |
| Object | Yuan dynasty (emerging) |
—
|
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: Yuan dynasty (emerging) | Statement: [Song Emperor Lizong, successorStateThreat, Yuan dynasty (emerging)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorStateThreat Context triple: [Song Emperor Lizong, successorStateThreat, Yuan dynasty (emerging)]
-
A.
successorStateOpponent
Indicates the resulting game state that follows the opponent’s move from a given current state.
-
B.
successorStatePressureFrom
chosen
Indicates the pressure exerted on a successor state by another entity, typically as a consequence or continuation of prior state conditions or actions.
-
C.
successorState
Indicates that one state directly follows another as the immediate next state in a sequence or process.
-
D.
successorStateSide2
Indicates that one state directly follows another as its immediate successor in the second dimension, perspective, or side of a state-transition relation.
-
E.
successorStateFlag
Indicates that a particular state directly follows another state in a defined sequence or process.
- 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_69ef96b7f330819090f315318ba6977e |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69fcef654d588190b29ecc76678d1aa0 |
completed | May 7, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69fcecdb97f48190b382b7d13be92dc0 |
completed | May 7, 2026, 7:49 p.m. |
Created at: April 27, 2026, 7:38 p.m.