Triple
T22456348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loarre Castle |
E555125
|
entity |
| Predicate | battlements |
P101353
|
FINISHED |
| Object | crenellated walls |
—
|
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: crenellated walls | Statement: [Loarre Castle, battlements, crenellated walls]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: battlements Context triple: [Loarre Castle, battlements, crenellated walls]
-
A.
battlementFeature
chosen
Indicates that one architectural element functions as a defensive battlement or is a structural feature of a battlement.
-
B.
fortifiedBuilding
Indicates that a building is strengthened or reinforced for defense against attacks or intrusions.
-
C.
opposedFortification
Indicates that one entity actively resisted, challenged, or worked against the strengthening or fortifying of another entity or location.
-
D.
castleOverlooks
Indicates that a castle is positioned so that it has a clear, elevated view over a particular area, object, or landscape.
-
E.
castle
Indicates that one entity is a castle associated with, located at, or serving as the stronghold or residence for another entity.
- 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b4f19708190a50f29598fb1a204 |
completed | April 29, 2026, 1:13 a.m. |
| PD | Predicate disambiguation | batch_69e898ad961c819098fd1e46129bddcc |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:48 p.m.