Triple
T37540828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lyra the Sunshard |
E933320
|
entity |
| Predicate | generatedCardSource |
P191136
|
FINISHED |
| Object | random Priest spell |
—
|
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: random Priest spell | Statement: [Lyra the Sunshard, generatedCardSource, random Priest spell]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: generatedCardSource Context triple: [Lyra the Sunshard, generatedCardSource, random Priest spell]
-
A.
generatedCardType
Indicates the type or category assigned to a card that has been generated.
-
B.
generatesCard
Indicates that one entity creates or produces a card for another entity or for some purpose.
-
C.
cardExample
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.
-
D.
cardVariant
Indicates that one card is a specific version or variation of another base card.
-
E.
legalCardsFrom
Indicates that the referenced cards are permitted or valid according to the rules or constraints defined by the specified source or authority.
- 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_69f76ec999288190ae26ec7b6aea7046 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcda3699948190adb57625bae08091 |
completed | May 7, 2026, 6:30 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fd16d08190b0aca6e19a632e99 |
completed | May 7, 2026, 6:25 p.m. |
| PDg | Predicate description generation | batch_69fcda35dc048190a3c90e15230900e0 |
completed | May 7, 2026, 6:30 p.m. |
Created at: May 3, 2026, 4:17 p.m.