Triple
T11416948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grey Lady ghost |
E270515
|
entity |
| Predicate | reputedLocation |
P40
|
FINISHED |
| Object | interior of Glamis Castle |
—
|
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: interior of Glamis Castle | Statement: [Grey Lady ghost, reputedLocation, interior of Glamis Castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reputedLocation Context triple: [Grey Lady ghost, reputedLocation, interior of Glamis Castle]
-
A.
recommendedLocation
Indicates that one entity suggests or endorses another entity as a suitable or preferred place for a particular purpose or activity.
-
B.
oftenLocatedAt
Indicates that an entity is frequently or commonly found at, or associated with being in, a particular location.
-
C.
locatedIn
chosen
Indicates that one entity exists or is situated within the spatial, administrative, or conceptual boundaries of another entity.
-
D.
notableLocation
Indicates that a location is especially significant, prominent, or noteworthy in relation to the subject.
-
E.
propertyLocation
Indicates the geographical place or address where a property is situated or found.
- 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_69d6aaddeaa8819088b30ef7b50598c9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d801b0236c81908122ce3fc7b4fde7 |
completed | April 9, 2026, 7:44 p.m. |
| PD | Predicate disambiguation | batch_69d7e70ffd708190b62a78ebcbce9f78 |
completed | April 9, 2026, 5:51 p.m. |
Created at: April 8, 2026, 9:34 p.m.