Triple
T5212873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gulf of Urabá |
E117674
|
entity |
| Predicate | approximateMaximumLength |
P34006
|
FINISHED |
| Object | 80 kilometres |
—
|
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: 80 kilometres | Statement: [Gulf of Urabá, approximateMaximumLength, 80 kilometres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateMaximumLength Context triple: [Gulf of Urabá, approximateMaximumLength, 80 kilometres]
-
A.
hasMaxLengthApprox
chosen
Indicates that something has a maximum length that is approximately equal to a specified value, allowing for some tolerance or imprecision.
-
B.
approximateBlockLength
Indicates that one entity specifies or estimates the length of a block in an approximate or non-exact manner.
-
C.
approximateLengthInMeters
Indicates the estimated or roughly measured length of something expressed in meters.
-
D.
hasApproximateMaximumWidth
Indicates that an entity’s maximum width is known only approximately, rather than as an exact value.
-
E.
maximumSegmentLength
Indicates the greatest allowable or observed length of a segment within a given context or structure.
- 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_69bd4464ba3c8190bc16b2ebbe42ddb0 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7a730e6c8190ae6082da41ee592a |
completed | March 20, 2026, 4:48 p.m. |
| PD | Predicate disambiguation | batch_69bd77bb4e8c819094b5ac7cf61512f9 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:47 p.m.