Triple
T37457719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shadowreaper Anduin |
E930839
|
entity |
| Predicate | relatedKeyword |
P65488
|
FINISHED |
| Object | Hero Power refresh |
—
|
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: Hero Power refresh | Statement: [Shadowreaper Anduin, relatedKeyword, Hero Power refresh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedKeyword Context triple: [Shadowreaper Anduin, relatedKeyword, Hero Power refresh]
-
A.
associatedKeyword
chosen
Indicates that one entity is linked to or characterized by a particular keyword used for identification, categorization, or retrieval.
-
B.
relatedPass
Indicates that one pass is associated with or connected to another pass in some relevant way.
-
C.
relatedToTerm
Indicates a general, non-specific relationship or association between one term and another.
-
D.
relatedMatchType
Indicates that two entities are connected through a specified type or category of relationship that defines how they are considered related or matched.
-
E.
relatedTLD
Indicates that one top-level domain (TLD) has an association or connection with another TLD, such as similarity, shared purpose, or contextual relevance.
- 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_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a13a1308190a202df66f4781855 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:17 p.m.