Triple
T27547175
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Amistad |
E695393
|
entity |
| Predicate | borderRiverSection |
P115250
|
FINISHED |
| Object | Rio Grande |
—
|
NE NERFINISHED |
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: Rio Grande | Statement: [Lake Amistad, borderRiverSection, Rio Grande]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderRiverSection Context triple: [Lake Amistad, borderRiverSection, Rio Grande]
-
A.
borderSectionOf
chosen
Indicates that one entity represents a specific segment or portion of the overall border of another entity.
-
B.
borderRiverContext
Indicates that a river serves as or is involved in forming the boundary between two geographic or political regions within a specific contextual setting.
-
C.
bordersAcrossRiver
Indicates that two regions or entities share a boundary with each other that is separated or defined by a river.
-
D.
borderSectionName
Indicates the specific named segment or portion of a border that is associated with or applies to an entity.
-
E.
crossBorderSection
Indicates a section or segment that extends across or passes from one jurisdiction, region, or country into another.
- 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_69ef5386c3e08190bfe33aa326e1f72b |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69fcef654d588190b29ecc76678d1aa0 |
completed | May 7, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69fcecdb97f48190b382b7d13be92dc0 |
completed | May 7, 2026, 7:49 p.m. |
Created at: April 27, 2026, 1:33 p.m.