Triple
T37464444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | League of E.V.I.L. |
E930998
|
entity |
| Predicate | hasCardTypeAssociation |
P128043
|
FINISHED |
| Object | Hero cards |
—
|
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 cards | Statement: [League of E.V.I.L., hasCardTypeAssociation, Hero cards]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCardTypeAssociation Context triple: [League of E.V.I.L., hasCardTypeAssociation, Hero cards]
-
A.
hasCardAssociation
Indicates that there is an established relationship or linkage between an entity and a specific card or card-related system.
-
B.
hasMatchCardType
Indicates that two or more items share the same card type or that an item is associated with a specific matching card type.
-
C.
hasCreditCardVariant
Indicates that one credit card is a specific version, type, or variation of another credit card.
-
D.
hasAssociatedType
chosen
Indicates that one entity is linked to another entity that specifies its type, category, or classification.
-
E.
hasTypeOfCredit
Indicates that an entity is associated with or characterized by a specific type or category of credit.
- 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_6a0010e46d948190a51111b5270fade7 |
completed | May 10, 2026, 5 a.m. |
| PD | Predicate disambiguation | batch_6a001061d34c8190bfe73f3d7c061eb7 |
completed | May 10, 2026, 4:58 a.m. |
Created at: May 3, 2026, 4:17 p.m.