Triple
T763436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palais Garnier |
E16120
|
entity |
| Predicate | hasUndergroundFeature |
P15152
|
FINISHED |
| Object | subterranean lake |
—
|
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: subterranean lake | Statement: [Palais Garnier, hasUndergroundFeature, subterranean lake]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUndergroundFeature Context triple: [Palais Garnier, hasUndergroundFeature, subterranean lake]
-
A.
hasUndergroundSection
chosen
Indicates that an entity includes a portion or segment that is located below ground level.
-
B.
hasUndergroundSlide
Indicates that one entity features or includes an underground slide connecting it to another location or structure.
-
C.
hasInteriorFeature
Indicates that an entity contains or includes a specific feature within its interior space.
-
D.
hasUrbanFeature
Indicates that a place or area possesses a specific urban element or infrastructure feature (such as roads, parks, or buildings) as part of its built environment.
-
E.
hasCaves
Indicates that one entity possesses, contains, or is characterized by the presence of caves.
- 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_69a493684ee48190bd43b7c78da4aec8 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a69c8c448190a036a04fd8fdd2c2 |
completed | March 1, 2026, 8:50 p.m. |
| PD | Predicate disambiguation | batch_69a4a506106081909ef97a679ff00a5a |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:37 p.m.