Triple
T30074006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dent (clockmaking firm) |
E764264
|
entity |
| Predicate | hasNotableClock |
P5737
|
FINISHED |
| Object | Great Clock of Westminster |
—
|
NE NERFINISHED |
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: Great Clock of Westminster | Statement: [Dent (clockmaking firm), hasNotableClock, Great Clock of Westminster]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableClock Context triple: [Dent (clockmaking firm), hasNotableClock, Great Clock of Westminster]
-
A.
hasClock
chosen
Indicates that one entity possesses, contains, or is equipped with a clock.
-
B.
hasClockMaker
Indicates that an entity has, is associated with, or was created/maintained by a specific clock maker.
-
C.
hasClockInput
Indicates that an entity receives a clock signal from another entity as an input for timing or synchronization purposes.
-
D.
usesClockSystem
Indicates that one entity employs or operates according to the clock or timekeeping system defined or provided by another entity.
-
E.
hasClockFigures
Indicates that an object features or includes figures or representations that are part of a clock.
- 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_69f22472eee081909791dc372aa766e9 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a00119d821c8190874786391b27ef23 |
completed | May 10, 2026, 5:03 a.m. |
| PD | Predicate disambiguation | batch_6a001143fb6881909ac0ae8bfea04351 |
completed | May 10, 2026, 5:01 a.m. |
Created at: April 29, 2026, 7:01 p.m.