Triple
T16751302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Three Sisters |
E407086
|
entity |
| Predicate | elevationAboveValleyFloor |
P66809
|
FINISHED |
| Object | about 300 metres |
—
|
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 300 metres | Statement: [Three Sisters, elevationAboveValleyFloor, about 300 metres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: elevationAboveValleyFloor Context triple: [Three Sisters, elevationAboveValleyFloor, about 300 metres]
-
A.
elevationAboveValley
chosen
Indicates the vertical height or altitude of an entity measured relative to the lowest point of the surrounding valley.
-
B.
valleyHeightAboveGround
Indicates the vertical distance between the valley’s lowest point and the surrounding ground level.
-
C.
elevationRelativeToCanyonFloor
Indicates the vertical height or altitude of something measured relative to the canyon floor as the reference level.
-
D.
deckHeightAboveValley
Indicates that the height of a deck is measured relative to, and positioned above, the elevation of a valley.
-
E.
elevationAboveLake
Indicates the vertical height or altitude of something relative to the surface level of a specified lake.
- 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_69d8838ffb088190a0b11149929006bf |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3aa271de48190b4a535408aeef734 |
completed | April 18, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69e319cbd79c8190a03587a61c18bec0 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:21 a.m.