Triple
T38586707
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Destruction of Theramore by Garrosh Hellscream using a mana bomb |
E932361
|
entity |
| Predicate | weaponSource |
P6948
|
FINISHED |
| Object | focusing iris |
—
|
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: focusing iris | Statement: [Destruction of Theramore by Garrosh Hellscream using a mana bomb, weaponSource, focusing iris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weaponSource Context triple: [Destruction of Theramore by Garrosh Hellscream using a mana bomb, weaponSource, focusing iris]
-
A.
weaponsBay
Indicates that one entity serves as the weapons bay (storage or housing area for weapons) of another entity.
-
B.
weapon
chosen
Indicates that one entity is used as a weapon by, or serves as the weapon of, another entity.
-
C.
weaponDepicted
Indicates that a weapon is visually represented or shown in association with an entity.
-
D.
weaponUsedOn
Indicates that a particular weapon was employed or applied against a specific target or entity.
-
E.
weaponOfInterest
Indicates that an entity is a weapon that is specifically relevant, notable, or targeted for attention within a given context or scenario.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.