Triple
T37540884
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Echo (Hearthstone keyword) |
E933321
|
entity |
| Predicate | exampleCard |
P188366
|
FINISHED |
| Object | Face Collector |
—
|
NE NERFINISHED |
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: Face Collector | Statement: [Echo (Hearthstone keyword), exampleCard, Face Collector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exampleCard Context triple: [Echo (Hearthstone keyword), exampleCard, Face Collector]
-
A.
cardExample
chosen
Indicates that something is an illustrative or sample instance of a card (such as a prototype, demo, or example card) rather than a primary or production card.
-
B.
cardText
Indicates that one entity is the textual content displayed on a card associated with another entity.
-
C.
cardVariant
Indicates that one card is a specific version or variation of another base card.
-
D.
cardClass
Indicates the classification or category to which a given card belongs within a defined card system or schema.
-
E.
containsCard
Indicates that one entity includes or holds a specific card as part of its contents or collection.
- 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_69f76ec999288190ae26ec7b6aea7046 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:17 p.m.