Triple
T28634604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khitan people |
E724740
|
entity |
| Predicate | successorStateFoundedByElites |
P3025
|
FINISHED |
| Object | Qara Khitai |
—
|
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: Qara Khitai | Statement: [Khitan people, successorStateFoundedByElites, Qara Khitai]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorStateFoundedByElites Context triple: [Khitan people, successorStateFoundedByElites, Qara Khitai]
-
A.
successorColony
Indicates that one colony directly follows and replaces another colony as its historical or political successor.
-
B.
successorFormation
Indicates that one entity comes into existence as the direct replacement or continuation of another, typically following the end or transformation of the predecessor.
-
C.
successorState
chosen
Indicates that one state directly follows another as the immediate next state in a sequence or process.
-
D.
successorForce
Indicates that one force or power succeeds, replaces, or takes over the role of another force.
-
E.
successorFoundedBy
Indicates that an entity was founded by the successor of another specified entity.
- 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_69f01d8328c48190bc0e5f9b9b848582 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69fd7b0503a08190ba07338365b6fcc9 |
completed | May 8, 2026, 5:56 a.m. |
| PD | Predicate disambiguation | batch_69fd7a9733dc81909199f453c0cc2bc1 |
completed | May 8, 2026, 5:54 a.m. |
Created at: April 28, 2026, 4:39 a.m.