Triple
T38587560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the Great Forge |
E932378
|
entity |
| Predicate | hasNearbyNPCType |
P193931
|
FINISHED |
| Object | blacksmithing trainer NPCs |
—
|
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: blacksmithing trainer NPCs | Statement: [the Great Forge, hasNearbyNPCType, blacksmithing trainer NPCs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyNPCType Context triple: [the Great Forge, hasNearbyNPCType, blacksmithing trainer NPCs]
-
A.
hasNearbyEntityType
chosen
Indicates that an entity has at least one other entity of a specified type located within a defined nearby spatial or contextual range.
-
B.
hasNotableNearbyEntity
Indicates that one entity has another significant or noteworthy entity located in its close physical or contextual proximity.
-
C.
hasNearbyFunction
Indicates that one entity has another entity located close by that serves a related or supportive function.
-
D.
hasNearbyEventType
Indicates that an event of a specified type occurs in close spatial or contextual proximity to a given reference entity or location.
-
E.
hasNearbyEvent
Indicates that an event occurs close in space or time to the referenced entity.
- 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_6a00d08e8fac8190b59359134e6e1c03 |
completed | May 10, 2026, 6:38 p.m. |
| PD | Predicate disambiguation | batch_6a00d0127c088190a6f5b360450af113 |
completed | May 10, 2026, 6:36 p.m. |
Created at: May 3, 2026, 4:32 p.m.