Triple
T14265864
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U3 at Hallesches Tor |
E353641
|
entity |
| Predicate | hasStationTypeAt |
P113495
|
FINISHED |
| Object | underground station at Hallesches Tor |
—
|
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: underground station at Hallesches Tor | Statement: [U3 at Hallesches Tor, hasStationTypeAt, underground station at Hallesches Tor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStationTypeAt Context triple: [U3 at Hallesches Tor, hasStationTypeAt, underground station at Hallesches Tor]
-
A.
hasStationAt
Indicates that an entity maintains or operates a station located at a specified place.
-
B.
hasStationFunction
Indicates that an entity serves in a particular functional role or capacity at a station.
-
C.
hasStationStructure
Indicates that an entity possesses or is associated with a particular station-related physical structure.
-
D.
hasComponentStation
Indicates that an entity includes or is associated with a specific station as one of its component parts.
-
E.
hasStationNear
Indicates that one entity has a station located in close proximity to another entity.
- 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_69d8278c43e08190824146f4632b89a5 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6357a8188190ba518a486521052b |
completed | April 14, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69de2a7d586c8190846ff242bbf5ac53 |
completed | April 14, 2026, 11:52 a.m. |
| PDg | Predicate description generation | batch_69de2e07d1f88190bdcd20967e484718 |
completed | April 14, 2026, 12:07 p.m. |
Created at: April 10, 2026, 1:09 a.m.