Triple
T31475263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tower 2000 |
E802973
|
entity |
| Predicate | hasElevatorConnectionTo |
P87576
|
FINISHED |
| Object | Bagration Bridge |
—
|
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: Bagration Bridge | Statement: [Tower 2000, hasElevatorConnectionTo, Bagration Bridge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasElevatorConnectionTo Context triple: [Tower 2000, hasElevatorConnectionTo, Bagration Bridge]
-
A.
hasElevatorConnection
chosen
Indicates that there is a direct elevator-based connection or access route between two locations or entities.
-
B.
hasElevators
Indicates that one entity is equipped with or contains one or more elevators for vertical transportation.
-
C.
hasElevatorOffice
Indicates that an office is equipped with or accessible via an elevator.
-
D.
hasEscalators
Indicates that one entity is equipped with or contains escalators that can be used for movement between different levels or areas.
-
E.
hasNumberOfElevatorBanks
Indicates the relationship specifying how many distinct elevator banks are present in or associated with a given 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_69f348c9477c8190bc0a21f6d482d2fc |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f72921cf2c8190909bb53f78bcc890 |
completed | May 3, 2026, 10:53 a.m. |
| PD | Predicate disambiguation | batch_69f7283d8cec8190b524c144948bc4ec |
completed | May 3, 2026, 10:49 a.m. |
Created at: April 30, 2026, 9:28 p.m.