Triple
T36905915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Leo |
E912775
|
entity |
| Predicate | fortressLocatedOn |
P186671
|
FINISHED |
| Object | sheer rocky cliff |
—
|
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: sheer rocky cliff | Statement: [San Leo, fortressLocatedOn, sheer rocky cliff]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fortressLocatedOn Context triple: [San Leo, fortressLocatedOn, sheer rocky cliff]
-
A.
fortressLocation
Indicates that a fortress is located at or in a specified place or geographic area.
-
B.
fortressOriginallyBuiltBy
Indicates that a particular fortress was initially constructed by a specified builder or group.
-
C.
fortifiedSite
Indicates a site that has been strengthened or defended with protective structures or measures against attack.
-
D.
fortifiedAsPartOf
Indicates that one entity has been strengthened or reinforced as a component or segment of a larger defensive structure or system.
-
E.
countryOfFortress
Indicates that a fortress is located within and belongs to the territory of a specific country.
- 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_69f76e879768819085c2fb31a6a5b44b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fe1a1ca4819084c196f0041f0be2 |
completed | May 5, 2026, 2:26 p.m. |
| PD | Predicate disambiguation | batch_69f7cf79ddb08190a083405cccc14137 |
completed | May 3, 2026, 10:43 p.m. |
| PDg | Predicate description generation | batch_69f9fd66eed48190bdc26a8def328c2d |
completed | May 5, 2026, 2:23 p.m. |
Created at: May 3, 2026, 4:13 p.m.