Triple
T32885020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragsholm Castle |
E841172
|
entity |
| Predicate | hasGhostLegend |
P58281
|
FINISHED |
| Object | White Lady |
—
|
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: White Lady | Statement: [Dragsholm Castle, hasGhostLegend, White Lady]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGhostLegend Context triple: [Dragsholm Castle, hasGhostLegend, White Lady]
-
A.
hasGhostCharacter
chosen
Indicates that an entity includes, features, or is associated with a character that is a ghost.
-
B.
hasCultOrLegend
Indicates that an entity is associated with, or is the subject of, a cult, myth, or legendary tradition.
-
C.
hasGhostHouse
Indicates that an entity possesses, contains, or is associated with a house believed to be haunted or inhabited by ghosts.
-
D.
hasGhostTown
Indicates that a place contains or is associated with a ghost town, typically an abandoned or largely uninhabited settlement.
-
E.
hasMythicalFigure
Indicates that one entity is associated with, features, or includes a particular mythical or legendary figure.
- 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_69f349446e288190a70c05bcc4d81172 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d16f5cb881908eed141afaaa0b51 |
completed | May 3, 2026, 4:39 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe45554819089cbbd538d992132 |
completed | May 3, 2026, 4:32 a.m. |
Created at: May 1, 2026, 1:18 a.m.