Triple
T36659982
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queen Elizabeth |
E905092
|
entity |
| Predicate | seeksAllianceWith |
P68915
|
FINISHED |
| Object | Duchess of York |
—
|
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: Duchess of York | Statement: [Queen Elizabeth, seeksAllianceWith, Duchess of York]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seeksAllianceWith Context triple: [Queen Elizabeth, seeksAllianceWith, Duchess of York]
-
A.
soughtAllianceWith
chosen
Indicates that one entity actively attempted to form an alliance or cooperative partnership with another entity.
-
B.
alliance
Indicates a formal cooperative relationship between entities who agree to support each other in shared goals or interests.
-
C.
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.
-
D.
reasonForAlliance
Indicates that one entity’s motivation, cause, or justification for forming an alliance is based on another specified factor or entity.
-
E.
restoredAllianceWith
Indicates that a previously broken or weakened alliance between two entities has been repaired and reestablished.
- 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_69f76e6e3b908190970251b30f76ad71 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c77b118881908cad488643e61e8a |
completed | May 3, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69f7c4796ebc819084a0dc08505e5f14 |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:11 p.m.