Triple
T23796308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louvre-Lens |
E588549
|
entity |
| Predicate | builtOnFormer |
P72777
|
FINISHED |
| Object | coal mining site |
—
|
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: coal mining site | Statement: [Louvre-Lens, builtOnFormer, coal mining site]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: builtOnFormer Context triple: [Louvre-Lens, builtOnFormer, coal mining site]
-
A.
builtOn
Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
-
B.
hasFormerBuilding
Indicates that an entity previously occupied or used a different building, which is identified as its former building.
-
C.
laterBuiltOverBy
chosen
Indicates that a structure or feature was constructed at a later time on top of, or replacing, an earlier one.
-
D.
wasOriginallyBuiltAs
Indicates that an object or structure was initially constructed for a particular purpose, function, or role, which may differ from its current use.
-
E.
builtFrom
Indicates that one entity is constructed, composed, or formed using another entity as its material, component, or source.
- 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_69e25d15db58819092ac1e6791696fd9 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c6dc94d481908800385a58d2c452 |
completed | April 29, 2026, 8:52 a.m. |
| PD | Predicate disambiguation | batch_69f155fe300481909bd617443228df65 |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:48 p.m.