Triple
T38584509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Shattered Halls |
E932315
|
entity |
| Predicate | neighborInstance |
P191754
|
FINISHED |
| Object | Hellfire Ramparts |
—
|
NE NERFINISHED |
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: Hellfire Ramparts | Statement: [The Shattered Halls, neighborInstance, Hellfire Ramparts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: neighborInstance Context triple: [The Shattered Halls, neighborInstance, Hellfire Ramparts]
-
A.
neighborWorld
Indicates that two worlds are adjacent or directly neighboring each other in some defined spatial or structural sense.
-
B.
neighborCharacter
Indicates that one character is located adjacent to or next to another character in a given context.
-
C.
innerNeighbor
Indicates that one entity is directly adjacent to another entity on the inside or interior side of a boundary or structure.
-
D.
residesNear
Indicates that one entity lives or is located in close physical proximity to another entity.
-
E.
neighborDescription
Indicates that one entity is described as being located near or adjacent to another entity, typically sharing a close spatial or contextual proximity.
- 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_69fce7671f108190bf3ebf54339068b5 |
completed | May 7, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69fce5b5a84c81908ac1b5b9f08d48d0 |
completed | May 7, 2026, 7:19 p.m. |
| PDg | Predicate description generation | batch_69fce76669408190b1beef8899a8a5e2 |
completed | May 7, 2026, 7:26 p.m. |
Created at: May 3, 2026, 4:32 p.m.