Triple
T28448142
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caves of Han-sur-Lesse |
E715897
|
entity |
| Predicate | hasMaximumChamberHeight |
P129310
|
FINISHED |
| Object | over 100 meters |
—
|
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: over 100 meters | Statement: [Caves of Han-sur-Lesse, hasMaximumChamberHeight, over 100 meters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMaximumChamberHeight Context triple: [Caves of Han-sur-Lesse, hasMaximumChamberHeight, over 100 meters]
-
A.
maximumChamberHeight
chosen
Indicates the greatest vertical distance from the lowest to the highest point within a specified chamber.
-
B.
hasChamberWidth
Indicates that an entity possesses a chamber whose width has a specified value or range.
-
C.
hasMainChamberVolume
Indicates that an entity (such as a device or container) possesses a primary internal chamber characterized by a specific volume.
-
D.
hasChamberLength
Indicates the length measurement of a chamber associated with an entity.
-
E.
hasChamberAbove
Indicates that one chamber is positioned vertically above another chamber in a spatial or structural arrangement.
- 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_69efd6b44550819094ae991b553d9fc3 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69fec8aef1d8819094c7fd7074038e6b |
completed | May 9, 2026, 5:39 a.m. |
| PD | Predicate disambiguation | batch_69fec639876481908efd84a3631a4271 |
completed | May 9, 2026, 5:29 a.m. |
Created at: April 28, 2026, 1:50 a.m.