Triple
T25075837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shards of Honor |
E628044
|
entity |
| Predicate | antagonistTurnedAlly |
P93243
|
FINISHED |
| Object | Aral Vorkosigan |
—
|
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: Aral Vorkosigan | Statement: [Shards of Honor, antagonistTurnedAlly, Aral Vorkosigan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: antagonistTurnedAlly Context triple: [Shards of Honor, antagonistTurnedAlly, Aral Vorkosigan]
-
A.
enemyTurnedAlly
chosen
Indicates that an entity that was previously an enemy has changed sides and is now acting as an ally.
-
B.
formerAllyOf
Indicates that an entity was once an ally of another entity but that alliance has since ended.
-
C.
formerEnemyOf
Indicates that one entity was previously an enemy of another entity, but that adversarial relationship no longer holds.
-
D.
temporarilyEnemyOf
Indicates a relationship where two entities are in a state of enmity or opposition for a limited, non-permanent period of time.
-
E.
antagonistOf
Indicates a relationship where one entity actively opposes, conflicts with, or serves as an adversary to another.
- 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_69e2ff2e73f881909992bf3eda5c25cb |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f45d1966c08190997f5ff8880a3314 |
completed | May 1, 2026, 7:58 a.m. |
| PD | Predicate disambiguation | batch_69f442c861188190967655c6d8012380 |
completed | May 1, 2026, 6:06 a.m. |
Created at: April 18, 2026, 6:21 a.m.