Triple
T21757589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leap Castle |
E537079
|
entity |
| Predicate | allegedToBeHauntedBy |
P143816
|
FINISHED |
| Object | Elemental spirit |
—
|
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: Elemental spirit | Statement: [Leap Castle, allegedToBeHauntedBy, Elemental spirit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allegedToBeHauntedBy Context triple: [Leap Castle, allegedToBeHauntedBy, Elemental spirit]
-
A.
isHauntedLocation
chosen
Indicates that a location is supernaturally affected or inhabited by ghosts, spirits, or other paranormal entities.
-
B.
haunts
Indicates that one entity persistently appears in, lingers around, or psychologically troubles another entity or place, often in a recurring or unsettling way.
-
C.
associatedWithApparition
Indicates a relationship where something is linked or connected to an apparition, such as being caused by, accompanying, or characterizing that apparition.
-
D.
apparitionFrequency
Indicates how often an entity appears, manifests, or becomes perceptible within a given context or timeframe.
-
E.
apparitionWitnessCount
Indicates the number of distinct observers who witnessed a particular apparition event.
- 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_69e0c46eab808190b848242d63a17c47 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01d8f64d881909cf10fd420153b09 |
completed | April 28, 2026, 2:38 a.m. |
| PD | Predicate disambiguation | batch_69e6969e46088190b13d6e9025775ea3 |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:50 p.m.