Triple
T38589989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashkandi, Greatsword of the Brotherhood |
E932430
|
entity |
| Predicate | lootDifficulty |
P191241
|
FINISHED |
| Object | high |
—
|
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: high | Statement: [Ashkandi, Greatsword of the Brotherhood, lootDifficulty, high]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lootDifficulty Context triple: [Ashkandi, Greatsword of the Brotherhood, lootDifficulty, high]
-
A.
lootLevelOriginalHeroic
Indicates the original heroic difficulty loot level associated with an entity or encounter.
-
B.
lootValue
Indicates the total worth or value assigned to items obtained as loot in a given context or event.
-
C.
LootType
Indicates the type or category of loot associated with an entity or event.
-
D.
lootPreference
Indicates a relationship where one entity has a favored choice or priority regarding the distribution or selection of loot.
-
E.
difficultySource
Indicates that one entity is the cause, origin, or contributing factor to the difficulty or challenge experienced in relation to another entity or situation.
- 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_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. |
| PDg | Predicate description generation | batch_69fcdaa2bfc08190beccabb0f1782d0d |
completed | May 7, 2026, 6:32 p.m. |
Created at: May 3, 2026, 4:32 p.m.