Triple
T1500903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Franklin D. Roosevelt |
E29792
|
entity |
| Predicate | hasAdvertisingCorridors |
P17433
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Franklin D. Roosevelt, hasAdvertisingCorridors, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAdvertisingCorridors Context triple: [Franklin D. Roosevelt, hasAdvertisingCorridors, yes]
-
A.
hasCorridor
Indicates that one entity includes, is connected by, or provides access through a corridor to another entity.
-
B.
hasServiceOnCorridor
Indicates that a service operates along, or is provided on, a specific corridor or route.
-
C.
hasConcessions
chosen
Indicates that one entity provides or contains concession facilities, services, or rights (such as food, drink, or merchandise sales) for another entity or within a given context.
-
D.
hasSignage
Indicates that appropriate signs or visual markers are present to convey information, directions, warnings, or identification related to the associated entity.
-
E.
hasDriveThroughLocations
Indicates that an entity operates or includes locations where customers can receive services or make purchases without leaving their vehicles.
- 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_69a498dba1d8819093b46a3a8d2485f1 |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c6f2d7f881909188a3e5614335cd |
completed | March 1, 2026, 11:08 p.m. |
| PD | Predicate disambiguation | batch_69a4c48a8cf48190a6ebf8d44a608a06 |
completed | March 1, 2026, 10:58 p.m. |
Created at: March 1, 2026, 8:12 p.m.