Triple
T37460789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spectral Knight |
E930910
|
entity |
| Predicate | targetingRule |
P199357
|
FINISHED |
| Object | cannot be targeted by friendly spells |
—
|
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: cannot be targeted by friendly spells | Statement: [Spectral Knight, targetingRule, cannot be targeted by friendly spells]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetingRule Context triple: [Spectral Knight, targetingRule, cannot be targeted by friendly spells]
-
A.
targetedRuler
Indicates that an entity intentionally directed hostile or coercive actions specifically against a ruling individual or authority figure.
-
B.
targetedCondition
Indicates that an action, intervention, or entity is specifically directed toward affecting, treating, or addressing a particular condition.
-
C.
targetedPolicy
Indicates that a policy is specifically directed at, or designed to affect, a particular subset of entities rather than applying broadly.
-
D.
usesTargetingSystem
Indicates that an entity employs or relies on a specific targeting system to aim at or select a target.
-
E.
targetScoreRule
Indicates the rule or criteria used to determine the target score to be achieved or applied in a given context.
- F. None of above. chosen
Provenance (4 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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff2fbae9b48190847eefa1c227d43e |
completed | May 9, 2026, 12:59 p.m. |
| PD | Predicate disambiguation | batch_69ff2f2218048190a32224a648182b5d |
completed | May 9, 2026, 12:57 p.m. |
| PDg | Predicate description generation | batch_69ff2fb9e46c8190b36b3e0bc84f114c |
completed | May 9, 2026, 12:59 p.m. |
Created at: May 3, 2026, 4:17 p.m.