Triple
T8928652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spokane Street Viaduct |
E212597
|
entity |
| Predicate | wideningCompleted |
P57479
|
FINISHED |
| Object | 2012 |
—
|
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: 2012 | Statement: [Spokane Street Viaduct, wideningCompleted, 2012]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wideningCompleted Context triple: [Spokane Street Viaduct, wideningCompleted, 2012]
-
A.
wideningCompletionYear
chosen
Indicates the year in which a widening project or expansion of something (such as a structure, route, or system) was completed.
-
B.
wideningProgram
Indicates that one entity is a program or process that increases the scope, capacity, or extent of another entity.
-
C.
closureCompleted
Indicates that a previously initiated closure process or shutdown has been fully and successfully completed.
-
D.
unificationCompleted
Indicates that a previously initiated unification process between entities has been successfully completed.
-
E.
compositionCompleted
Indicates that the process of composing or creating something (such as a work, document, or piece) has been fully completed.
- 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_69ca8395c438819087d7cb844ab5990c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc667470308190a75ba63de803e3a2 |
completed | April 1, 2026, 12:27 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed3286c8190a21de2ee11f2639f |
completed | March 31, 2026, 11:54 p.m. |
Created at: March 30, 2026, 6:57 p.m.