Triple
T5244910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fort Fincastle |
E118434
|
entity |
| Predicate | builderRole |
P3143
|
FINISHED |
| Object | Governor of the Bahamas |
—
|
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: Governor of the Bahamas | Statement: [Fort Fincastle, builderRole, Governor of the Bahamas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: builderRole Context triple: [Fort Fincastle, builderRole, Governor of the Bahamas]
-
A.
builder
chosen
Indicates that an entity is responsible for constructing, creating, or assembling another entity.
-
B.
architecturalRole
Indicates the functional or design-related role that one entity plays within the structure, layout, or organization of another entity.
-
C.
designedRole
Indicates that one entity has been created, configured, or intended to serve a particular function, purpose, or role in relation to another entity.
-
D.
plannedRole
Indicates that an entity is expected or intended to assume a particular role or function in a planned or future context.
-
E.
roleInEngine
Indicates the specific function or responsibility an entity has within an engine or engine-like system.
- 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_69bd4468aacc8190a8196f71855cdf4f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7b4fa0ec8190bce3da09aa768726 |
completed | March 20, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69bd77c1397c8190a7fd844d7a396e54 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:49 p.m.