Triple
T12398024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krestovsky Bridge |
E296170
|
entity |
| Predicate | isOnIslandRoute |
P104622
|
FINISHED |
| Object | access route to Krestovsky Island |
—
|
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: access route to Krestovsky Island | Statement: [Krestovsky Bridge, isOnIslandRoute, access route to Krestovsky Island]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOnIslandRoute Context triple: [Krestovsky Bridge, isOnIslandRoute, access route to Krestovsky Island]
-
A.
isInIsland
Indicates that one entity is located within the geographic boundaries of an island.
-
B.
isOnSideOfIsland
Indicates that one entity is located on a particular side or shore of an island relative to some reference or division.
-
C.
meetsInIsland
Indicates that two or more entities meet with each other at a location that is an island.
-
D.
isIsland
Indicates that the subject entity is classified as an island, i.e., a landmass surrounded by water.
-
E.
isOnIslandArc
Indicates that one entity (typically a geographic or geological feature) is located on or belongs to an island arc.
- F. None of above. chosen
Provenance (4 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_69d6ad9f464c81909db36d7e96e34b9e |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fd448f08190af425a569d7ed158 |
completed | April 10, 2026, 6:22 p.m. |
| PD | Predicate disambiguation | batch_69d93ed4cea08190ad374d3f6a798053 |
completed | April 10, 2026, 6:17 p.m. |
| PDg | Predicate description generation | batch_69d93f607a88819089e89fd263ae9937 |
completed | April 10, 2026, 6:20 p.m. |
Created at: April 8, 2026, 9:54 p.m.