Triple
T2810019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kendall/MIT station |
E54144
|
entity |
| Predicate | hasAdjacentStationDirectionOutbound |
P43724
|
FINISHED |
| Object | Central station |
—
|
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: Central station | Statement: [Kendall/MIT station, hasAdjacentStationDirectionOutbound, Central station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAdjacentStationDirectionOutbound Context triple: [Kendall/MIT station, hasAdjacentStationDirectionOutbound, Central station]
-
A.
hasAdjacentStationOnLine1
Indicates that one station is directly next to another station along Line 1 in the network.
-
B.
adjacentStationSouth
Indicates that one station is directly to the south of another station, with no other station in between.
-
C.
adjacentToStation
Indicates that one entity is located next to or immediately beside a station.
-
D.
adjacentStationOnLine
Indicates that one station is directly next to another station along the same transit line, with no other station in between.
-
E.
adjacentStationNorth
Indicates that one station is directly adjacent to another station to its north.
- 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_69ab49dcee188190b5c6eca9ae9e3469 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abde335b38819090c70d5e2ca14d79 |
completed | March 7, 2026, 8:13 a.m. |
| PD | Predicate disambiguation | batch_69abdd0740208190911dc9c9546a79ae |
completed | March 7, 2026, 8:08 a.m. |
| PDg | Predicate description generation | batch_69abde0f4c648190b9812e64f30c39da |
completed | March 7, 2026, 8:13 a.m. |
Created at: March 6, 2026, 9:59 p.m.