Triple
T8535553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kellie’s Castle |
E202067
|
entity |
| Predicate | localLegend |
P25724
|
FINISHED |
| Object | haunted by its builder’s 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: haunted by its builder’s spirit | Statement: [Kellie’s Castle, localLegend, haunted by its builder’s spirit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: localLegend Context triple: [Kellie’s Castle, localLegend, haunted by its builder’s spirit]
-
A.
legendLocation
chosen
Indicates the place or setting where a particular legend, myth, or traditional story is situated or associated.
-
B.
bestKnownLegend
Indicates that one entity is the most prominent or widely recognized legendary story or myth associated with another entity.
-
C.
legendaryHomeOf
Indicates that a place is traditionally or mythically regarded as the home or origin of a particular figure, group, or entity.
-
D.
localIdentity
Indicates that an entity’s identity or role is defined specifically within a particular local context, scope, or environment, rather than globally.
-
E.
localNickname
Indicates that an entity is known by a particular nickname within a specific local or regional context.
- 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_69ca832355b08190b8b6a4ab4a4a3554 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe6a295c88190a432a060ee73f04e |
completed | March 31, 2026, 3:22 p.m. |
| PD | Predicate disambiguation | batch_69cbd111bf988190be98c92a607c6456 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:17 p.m.