Triple
T24212294
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wall of Denial |
E600584
|
entity |
| Predicate | hasOracleText |
P139133
|
FINISHED |
| Object | Defender, flying, shroud |
—
|
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: Defender, flying, shroud | Statement: [Wall of Denial, hasOracleText, Defender, flying, shroud]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOracleText Context triple: [Wall of Denial, hasOracleText, Defender, flying, shroud]
-
A.
hasOracleOf
Indicates that one entity serves as a prophetic or divinatory source (an oracle) for another entity.
-
B.
hasOrb
Indicates that one entity possesses, holds, or is associated with an orb.
-
C.
hasEffectText
chosen
Indicates that a subject is associated with a textual description specifying its effect or impact.
-
D.
commandedByOracleTo
Indicates that an entity performs or undertakes an action as a result of being ordered or instructed to do so by an oracle.
-
E.
hasFictionalSignText
Indicates that an entity bears or is associated with text appearing on a fictional sign (e.g., wording depicted on an in-universe sign).
- 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_69e2953344c48190875730c7d52112a0 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f2820401bc81909ae1837b41c85526 |
completed | April 29, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69f1c43e55688190b55fc20274ed471c |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:55 p.m.