Triple
T36854122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Columbus Monument, Barcelona |
E910747
|
entity |
| Predicate | elevationPlatformHeight |
P105499
|
FINISHED |
| Object | about 50 m |
—
|
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: about 50 m | Statement: [Columbus Monument, Barcelona, elevationPlatformHeight, about 50 m]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: elevationPlatformHeight Context triple: [Columbus Monument, Barcelona, elevationPlatformHeight, about 50 m]
-
A.
hasFloorElevation
Indicates that one entity has a specified vertical height or level above a reference point (such as sea level or ground) for its floor.
-
B.
elevationApproxMeters
Indicates the approximate elevation of an entity above sea level, measured in meters.
-
C.
elevationAtRim
Indicates the elevation value measured specifically at the rim or edge of a geographic or topographic feature.
-
D.
elevationBy
Indicates a relationship where one entity raises, increases, or enhances the level, status, or intensity of another entity.
-
E.
boardingElevation
chosen
Indicates the elevation at which boarding occurs for a vehicle or transport facility, typically relative to a standard reference level.
- 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_69f76e8033d48190a59274f86f13be48 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcab6e888881908ca9e18660928a40 |
completed | May 7, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69fc4562a5b88190bad48f083a6dcdfa |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:13 p.m.