Triple
T23021454
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Avenue de Champagne |
E573174
|
entity |
| Predicate | hasSubterraneanCellarsLength |
P54999
|
FINISHED |
| Object | tens of kilometers |
—
|
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: tens of kilometers | Statement: [Avenue de Champagne, hasSubterraneanCellarsLength, tens of kilometers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubterraneanCellarsLength Context triple: [Avenue de Champagne, hasSubterraneanCellarsLength, tens of kilometers]
-
A.
hasUndergroundCellarsLength
chosen
Indicates that an entity possesses underground cellars whose length is specified or measured.
-
B.
hasCellars
Indicates that one entity possesses or contains one or more cellars associated with it.
-
C.
undergroundCavernLength
Indicates the measured linear extent or distance from one end to the other of an underground cavern.
-
D.
undergroundCavernWidth
Indicates the horizontal extent or span of an underground cavern from one side to the other.
-
E.
hasUndergroundLength
Indicates the extent of an object or structure that lies below ground level, measured as its underground length.
- 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_69e245b821008190b0e09cb02092aae1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e9208081908fdbb8e21cacedde |
completed | April 29, 2026, 4:07 a.m. |
| PD | Predicate disambiguation | batch_69ef3ba004a48190885aece88efd1f52 |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 17, 2026, 3:52 p.m.