Triple
T4498441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grotte de l’Aven Armand |
E100755
|
entity |
| Predicate | approximateChamberDepthBelowSurface |
P16570
|
FINISHED |
| Object | about 100 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 100 metres | Statement: [Grotte de l’Aven Armand, approximateChamberDepthBelowSurface, about 100 metres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateChamberDepthBelowSurface Context triple: [Grotte de l’Aven Armand, approximateChamberDepthBelowSurface, about 100 metres]
-
A.
hasUndergroundDepth
Indicates that one entity has a specified vertical extent or depth located below the ground surface relative to another reference or context.
-
B.
depthMetresApprox
chosen
Indicates an approximate measurement of how deep something is in metres, rather than an exact value.
-
C.
hasAverageDepth
Indicates that an entity possesses a specified mean depth value, typically measured over its entire extent or area.
-
D.
elevationBelowGround
Indicates that one entity’s elevation is located beneath the ground surface or reference ground level.
-
E.
oceanDepthBelow
Indicates that one location or point in the ocean is situated at a greater depth (deeper below the surface) than 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_69bd43cdf15081909a4fa2585ff63b3e |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd56c065e88190934eb0b1632d79bb |
completed | March 20, 2026, 2:16 p.m. |
| PD | Predicate disambiguation | batch_69bd521671688190bc655d25fa77eba2 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1 p.m.