Triple
T6385926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Casa de Correos |
E143700
|
entity |
| Predicate | clockChimes |
P33984
|
FINISHED |
| Object | twelve chimes at midnight on New Year’s Eve |
—
|
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: twelve chimes at midnight on New Year’s Eve | Statement: [Casa de Correos, clockChimes, twelve chimes at midnight on New Year’s Eve]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clockChimes Context triple: [Casa de Correos, clockChimes, twelve chimes at midnight on New Year’s Eve]
-
A.
chimes
chosen
Indicates that one entity produces a clear, resonant ringing sound, often as a signal or in response to a particular time or event.
-
B.
clockType
Indicates the type or category of a clock associated with an entity (e.g., analog, digital, system clock, etc.).
-
C.
carillonType
Indicates the specific kind or classification of a carillon associated with an entity.
-
D.
numberOfBells
Indicates the quantity of bells associated with or present in a given entity or context.
-
E.
carillonMaker
Indicates a relationship where an entity is the maker or builder of a carillon.
- 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_69c008dac1ec81909cef8157ccd69962 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c068688bfc8190a28918d58d0cfd2e |
completed | March 22, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69c060eff524819094cee1c70a0c1ff4 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:34 p.m.