Triple
T37461532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | C’Thun’s Chosen |
E930928
|
entity |
| Predicate | providesDefense |
P129572
|
FINISHED |
| Object | Divine Shield body |
—
|
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: Divine Shield body | Statement: [C’Thun’s Chosen, providesDefense, Divine Shield body]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providesDefense Context triple: [C’Thun’s Chosen, providesDefense, Divine Shield body]
-
A.
providesDefence
chosen
Indicates that one entity offers protection or defensive support to another entity.
-
B.
defenseFunction
Indicates that an entity serves a protective or defensive role against threats, attacks, or harm to another entity or system.
-
C.
defenseIncludes
Indicates that a defense strategy, plan, or system contains or incorporates a particular component, measure, or element as part of it.
-
D.
defenseStatus
Indicates the current state or condition of an entity’s defensive posture or protective readiness in a given context.
-
E.
defensiveCapability
Indicates the ability or capacity of an entity to protect itself or others against threats, attacks, or harm.
- 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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fed357b2b4819084c709056a54461f |
completed | May 9, 2026, 6:25 a.m. |
| PD | Predicate disambiguation | batch_69fed103d9cc81909b11619745110c61 |
completed | May 9, 2026, 6:15 a.m. |
Created at: May 3, 2026, 4:17 p.m.