Triple
T31836124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palais Montcalm |
E812677
|
entity |
| Predicate | hasHighQuality |
P17855
|
FINISHED |
| Object | acoustics |
—
|
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: acoustics | Statement: [Palais Montcalm, hasHighQuality, acoustics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHighQuality Context triple: [Palais Montcalm, hasHighQuality, acoustics]
-
A.
hasHigherQualityThan
Indicates that one entity possesses a superior level of quality compared to another entity.
-
B.
hasHigh
chosen
Indicates that an entity possesses a high level, degree, or intensity of a specified attribute or property.
-
C.
hasHighPropertyValues
Indicates that the associated entity possesses property values that are above a defined or typical threshold.
-
D.
hasHighStructure
Indicates that an entity possesses a high degree of organization, complexity, or well-defined internal structure in relation to another entity or standard.
-
E.
hasHighMass
Indicates that an entity possesses a mass that is large or above a specified threshold relative to a given standard or context.
- 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_69f348ea7ffc8190a2ab43d80277cf59 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fe5ec9028081909ae3d6fbe2f4cbbc |
completed | May 8, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69fe5e1d715881909fc516fafc707644 |
completed | May 8, 2026, 10:05 p.m. |
Created at: April 30, 2026, 11:48 p.m.