Triple
T30218151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Branxholme Castle |
E768264
|
entity |
| Predicate | hasDefensiveType |
P195046
|
FINISHED |
| Object | border fortress |
—
|
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: border fortress | Statement: [Branxholme Castle, hasDefensiveType, border fortress]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDefensiveType Context triple: [Branxholme Castle, hasDefensiveType, border fortress]
-
A.
hasDefenseStrategy
Indicates that an entity employs or is associated with a particular plan or set of measures designed to protect against threats or attacks.
-
B.
hasBaseDefense
Indicates that an entity possesses a specified level or value of defensive capability in its default or starting state.
-
C.
hasDefensiveWork
Indicates that an entity possesses or is associated with a work focused on defense or protective functions.
-
D.
hasDefensiveAppearance
Indicates that an entity possesses a visual or structural trait that serves to protect it or deter potential threats.
-
E.
hasDefensivePositions
Indicates that an entity possesses or controls locations, structures, or arrangements specifically organized for defense against potential threats or attacks.
- F. None of above. chosen
Provenance (4 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_69f2247fd8b8819087fcf83cb7a05eb8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd9ff026a48190bfec33deeb3b2c43 |
completed | May 8, 2026, 8:33 a.m. |
| PD | Predicate disambiguation | batch_69fd97d805bc8190ba12f429d3ad04c7 |
completed | May 8, 2026, 7:59 a.m. |
| PDg | Predicate description generation | batch_69fd9fef7aac819089cc88dd3d00296d |
completed | May 8, 2026, 8:33 a.m. |
Created at: April 29, 2026, 7:34 p.m.