Triple
T34773891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anxi Protectorate |
E1002447
|
entity |
| Predicate | hasAlternativeCapital |
P112033
|
FINISHED |
| Object | Qocho |
—
|
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: Qocho | Statement: [Anxi Protectorate, hasAlternativeCapital, Qocho]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAlternativeCapital Context triple: [Anxi Protectorate, hasAlternativeCapital, Qocho]
-
A.
hasAlternativeBasis
Indicates that something is supported, justified, or founded on a different underlying reason, source, or principle than the primary or original one.
-
B.
alternativeCapital
chosen
Indicates that one location serves as an alternative or secondary capital city in relation to another primary capital.
-
C.
isAlternativeTo
Indicates that one entity can serve as a substitute or different option in place of another.
-
D.
hasAlternativeReferent
Indicates that an entity can also be referred to or identified by an alternative name, label, or reference.
-
E.
hasAlternativeBoard
Indicates that an entity is associated with a different or substitute governing or decision-making board from the primary one.
- 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_69f76db30a108190bb57ca95b873e5bb |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69fd8e5f7c4c8190ab8e2f2a7bb1bd79 |
completed | May 8, 2026, 7:18 a.m. |
| PD | Predicate disambiguation | batch_69fd8d8a16f08190b9e880901bfa44fe |
completed | May 8, 2026, 7:15 a.m. |
Created at: May 3, 2026, 3:59 p.m.