Triple
T28590362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yelü clan |
E723621
|
entity |
| Predicate | interactedWithDynasty |
P98921
|
FINISHED |
| Object | Song dynasty |
—
|
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: Song dynasty | Statement: [Yelü clan, interactedWithDynasty, Song dynasty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: interactedWithDynasty Context triple: [Yelü clan, interactedWithDynasty, Song dynasty]
-
A.
associatedWithDynasty
Indicates that an entity has a historical, political, cultural, or familial connection to a specific dynasty.
-
B.
dynastyInvolved
chosen
Indicates that a particular dynasty participates in, is associated with, or plays a role in the referenced event, process, or situation.
-
C.
associatedWithDynastyPolitics
Indicates a relationship where an entity is involved in, influenced by, or connected to the political activities, power structures, or governance associated with a particular dynasty.
-
D.
basedOnDynasty
Indicates that something is derived from, influenced by, or established on the foundation of a particular dynasty.
-
E.
dynastyAffected
Indicates that a particular dynasty is influenced, impacted, or changed in some way by another entity, event, or condition.
- 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_69f01d7f92e481909847f5f3f3174a89 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f757898fe48190b124dc7301672623 |
completed | May 3, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f754c484348190948d2a04ff228fb1 |
completed | May 3, 2026, 1:59 p.m. |
Created at: April 28, 2026, 4:20 a.m.