Triple
T36501993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nanzhao Kingdom |
E899354
|
entity |
| Predicate | inAllianceWith |
P600
|
FINISHED |
| Object | Tibetan Empire |
—
|
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: Tibetan Empire | Statement: [Nanzhao Kingdom, inAllianceWith, Tibetan Empire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inAllianceWith Context triple: [Nanzhao Kingdom, inAllianceWith, Tibetan Empire]
-
A.
soughtAllianceWith
Indicates that one entity actively attempted to form an alliance or cooperative partnership with another entity.
-
B.
alliance
chosen
Indicates a formal cooperative relationship between entities who agree to support each other in shared goals or interests.
-
C.
oftenAlliedWith
Indicates that one entity is frequently or habitually allied or aligned in cooperation with another entity.
-
D.
vassalOrAllyOf
Indicates that one entity is subordinate to, dependent on, or formally aligned in support of another entity, typically in a hierarchical or cooperative political or military relationship.
-
E.
hadTechnicalAllianceWith
Indicates that two entities formed a cooperative relationship focused on sharing or collaborating on technical knowledge, resources, or capabilities.
- 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_69f76e5b92088190933afda3f7531dd4 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1b91fd88190ab85afd626603769 |
completed | May 3, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:10 p.m.