Triple
T33538750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crescent City Connection Bridge No. 1 |
E859013
|
entity |
| Predicate | belongsToRoute |
P92683
|
FINISHED |
| Object | U.S. Route 90 Business |
—
|
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: U.S. Route 90 Business | Statement: [Crescent City Connection Bridge No. 1, belongsToRoute, U.S. Route 90 Business]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToRoute Context triple: [Crescent City Connection Bridge No. 1, belongsToRoute, U.S. Route 90 Business]
-
A.
belongsToFeature
Indicates that one entity is a component, attribute, or part of a larger feature or functionality associated with another entity.
-
B.
belongsToLine
chosen
Indicates that an entity is a member or component of a particular line or linear grouping.
-
C.
belongsToCru
Indicates that one entity is a member of, or affiliated with, a specific crew or organizational unit.
-
D.
belongsToModule
Indicates that something is a component or part of a specific module within a larger system or structure.
-
E.
belongsToMode
Indicates that something is associated with, or is a member of, a particular mode or operational state.
- 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_69f3497a5be08190a39b12736899e034 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff1f3f94fc819095955299f50ab4ce |
completed | May 9, 2026, 11:49 a.m. |
| PD | Predicate disambiguation | batch_69ff1ea47748819082f63d9b9d9c3e65 |
completed | May 9, 2026, 11:46 a.m. |
Created at: May 1, 2026, 1:39 a.m.