Triple
T30742215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | An Lushan |
E782721
|
entity |
| Predicate | capitalDuringRebellion |
P188791
|
FINISHED |
| Object | Luoyang |
—
|
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: Luoyang | Statement: [An Lushan, capitalDuringRebellion, Luoyang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalDuringRebellion Context triple: [An Lushan, capitalDuringRebellion, Luoyang]
-
A.
capitalDuringExile
Indicates that a location served as the temporary capital of a political entity while its primary leadership or government was in exile.
-
B.
capitalDuringCivilWar
Indicates that a location served as the capital of a political entity during a specified civil war period.
-
C.
capitalDuringReign
Indicates that a particular city or location served as the capital of a political entity during the reign of a specified ruler.
-
D.
capitalDuringEra
Indicates that a city or settlement served as the capital of a political entity during a specified historical era or time period.
-
E.
capitalDuringExistence
Indicates that a specified place served as the capital of an entity for some or all of the time that entity existed.
- 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_69f224aeb1588190897d395e8ed2acb8 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fbad1e94988190b86d447a68e65067 |
completed | May 6, 2026, 9:05 p.m. |
| PD | Predicate disambiguation | batch_69fba881b8e0819094790935152b99a1 |
completed | May 6, 2026, 8:45 p.m. |
| PDg | Predicate description generation | batch_69fbad1b3ba08190ad69e21461333f2e |
completed | May 6, 2026, 9:05 p.m. |
Created at: April 29, 2026, 8:38 p.m.