Triple
T6104974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Castle |
E136094
|
entity |
| Predicate | isBuiltOn |
P2012
|
FINISHED |
| Object | promontory above Lunan Bay |
—
|
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: promontory above Lunan Bay | Statement: [Red Castle, isBuiltOn, promontory above Lunan Bay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isBuiltOn Context triple: [Red Castle, isBuiltOn, promontory above Lunan Bay]
-
A.
builtOn
chosen
Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
-
B.
isBuiltFor
Indicates that one entity is specifically designed, intended, or optimized to serve, support, or accommodate another entity or purpose.
-
C.
builtAgainst
Indicates that one structure or object is constructed directly adjoining and supported by the side or surface of another.
-
D.
isBasedOn
Indicates that one entity is derived from, inspired by, or developed using the content, structure, or principles of another entity.
-
E.
implementedOn
Indicates that something (such as a feature, standard, or specification) is realized, executed, or put into effect within or on a particular platform, system, or environment.
- 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_69c0087dee9881909e3655be88208c01 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05b3f8e5481909e85a60aaf319f66 |
completed | March 22, 2026, 9:12 p.m. |
| PD | Predicate disambiguation | batch_69c049f80e2081909b7d84a104cda68d |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:13 p.m.