Triple
T21689548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boston Custom House (original 1840s building) |
E535321
|
entity |
| Predicate | clockTowerFunction |
P2494
|
FINISHED |
| Object | timekeeping for the city |
—
|
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: timekeeping for the city | Statement: [Boston Custom House (original 1840s building), clockTowerFunction, timekeeping for the city]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clockTowerFunction Context triple: [Boston Custom House (original 1840s building), clockTowerFunction, timekeeping for the city]
-
A.
clockTowerAdded
Indicates that a clock tower has been newly constructed or incorporated into an existing structure or location.
-
B.
timeballTowerFunction
Indicates that something serves the function or role of a time ball tower, typically used to signal standardized time visually.
-
C.
hasClockTower
chosen
Indicates that one entity possesses or features a clock tower as part of its structure or property.
-
D.
clockType
Indicates the type or category of a clock associated with an entity (e.g., analog, digital, system clock, etc.).
-
E.
clockInput
Indicates that one entity serves as a timing or clock signal input that controls or synchronizes the operation of another entity.
- 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_69e0c469b6ec8190aee4cadd1527db91 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef96ce2ff88190a6cbfff45bb6a04f |
completed | April 27, 2026, 5:03 p.m. |
| PD | Predicate disambiguation | batch_69e6969113cc8190ab69855ef5667e4b |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:44 p.m.