Triple
T1111098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Willis Avenue Bridge |
E25597
|
entity |
| Predicate | oldBridgeDemolished |
P10256
|
FINISHED |
| Object | 2011 |
—
|
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: 2011 | Statement: [Willis Avenue Bridge, oldBridgeDemolished, 2011]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oldBridgeDemolished Context triple: [Willis Avenue Bridge, oldBridgeDemolished, 2011]
-
A.
demolished
chosen
Indicates that one entity completely destroyed or razed another entity, typically a structure or object, so that it no longer exists in its previous form.
-
B.
demolishedToMakeWayFor
Indicates that one entity was intentionally destroyed or removed in order to create space for another entity or development.
-
C.
bridges
Indicates that one entity connects or links two or more other entities, allowing passage, transition, or interaction between them.
-
D.
hasMajorBridge
Indicates that one entity possesses or includes a primary or significant bridge associated with it.
-
E.
bridgeType
Indicates the specific kind or classification of a bridge associated with an 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_69a49428d4448190b3b36991ceae87ce |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bbd92a8c8190a16e55f3f739010f |
completed | March 1, 2026, 10:21 p.m. |
| PD | Predicate disambiguation | batch_69a4bb42990c819080db96478fd4977e |
completed | March 1, 2026, 10:18 p.m. |
Created at: March 1, 2026, 7:43 p.m.