Triple
T33112809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hall of Fire |
E847373
|
entity |
| Predicate | setInRealm |
P134555
|
FINISHED |
| Object | Lindon and Eriador narrative region |
—
|
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: Lindon and Eriador narrative region | Statement: [Hall of Fire, setInRealm, Lindon and Eriador narrative region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: setInRealm Context triple: [Hall of Fire, setInRealm, Lindon and Eriador narrative region]
-
A.
definesRealmAs
Indicates that one entity specifies or establishes another entity as its realm, domain, or scope of authority or applicability.
-
B.
setInUniverse
Indicates that something is located within, belongs to, or takes place in a particular fictional or conceptual universe.
-
C.
residesInRealm
chosen
Indicates that an entity lives or exists within a particular realm or domain.
-
D.
setInUniverseWith
Indicates that something is situated or takes place within a specified fictional or conceptual universe, sharing its setting and continuity.
-
E.
associatedWithRealm
Indicates a relationship where an entity is linked or connected to a particular realm, domain, or sphere of influence.
- 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_69f3495751a081909850af5843da40dc |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d6ec34a481908851cd68697cb88c |
completed | May 3, 2026, 5:02 a.m. |
| PD | Predicate disambiguation | batch_69f6d27224708190b31a541cebe0ff77 |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:27 a.m.