Triple
T38644887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Valkyrie |
E938689
|
entity |
| Predicate | cannotAttack |
P96069
|
FINISHED |
| Object | ground units |
—
|
LITERAL FINISHED |
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: ground units | Statement: [Valkyrie, cannotAttack, ground units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cannotAttack Context triple: [Valkyrie, cannotAttack, ground units]
-
A.
cannotTarget
chosen
Indicates that one entity is unable or not permitted to select or act upon another entity as a target.
-
B.
canAttackOnOpponentsTurn
Indicates that an entity is able to perform an attack during the opposing side’s turn rather than only on its own turn.
-
C.
hasAttackRestriction
Indicates that there is a limitation or condition placed on how, when, or whom an entity is allowed to attack.
-
D.
cannotDirectlyKill
Indicates that one entity is unable, either by rule, ability, or circumstance, to directly cause the death of another entity.
-
E.
forceAttacked
Indicates that one entity carried out an attack against another entity using force or coercive power.
- 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_69f76ed948ec81908ce7811608a8f359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd49f6dbac81909744373a357b7982 |
completed | May 8, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69fd48ed68f481908374183c66a6b055 |
completed | May 8, 2026, 2:22 a.m. |
Created at: May 3, 2026, 4:32 p.m.