Triple
T30742212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | An Lushan |
E782721
|
entity |
| Predicate | usurpedTitle |
P65651
|
FINISHED |
| Object | 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: emperor | Statement: [An Lushan, usurpedTitle, emperor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usurpedTitle Context triple: [An Lushan, usurpedTitle, emperor]
-
A.
usurpedFrom
Indicates that one entity has taken power, position, or property from another entity illegitimately or by force.
-
B.
usurpsThroneFrom
chosen
Indicates that one entity seizes control of a throne or rulership position that previously belonged to another entity, typically by force or illegitimate means.
-
C.
consideredUsurper
Indicates that one entity is regarded or treated by another as an illegitimate holder of power, position, or authority.
-
D.
laterUsurpedBy
Indicates that one entity, after some time has passed, is overthrown or replaced in power, position, or authority by another entity.
-
E.
associatedTitleAfterEnthronement
Indicates the formal title or designation that is linked to an individual specifically after they have been enthroned or installed in an official position.
- 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_69f224aeb1588190897d395e8ed2acb8 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f68f6a32f081909499d6ca20f35e55 |
completed | May 2, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69f686140aa08190a35f62572b2db9b6 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:38 p.m.