Triple
T38555937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Melton railway station |
E925243
|
entity |
| Predicate | distanceToWoodbridgeByRail |
P65643
|
FINISHED |
| Object | approximately 2 miles |
—
|
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: approximately 2 miles | Statement: [Melton railway station, distanceToWoodbridgeByRail, approximately 2 miles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceToWoodbridgeByRail Context triple: [Melton railway station, distanceToWoodbridgeByRail, approximately 2 miles]
-
A.
distanceToWoodbridge
Indicates the spatial distance between a given entity or location and Woodbridge.
-
B.
distanceToByRail
chosen
Indicates the distance between two locations when traveling via railway routes.
-
C.
distanceFromBaltimorePennStation
Indicates the measured distance between a given location and Baltimore Penn Station.
-
D.
distanceToRailhead
Indicates the measured distance between a location or object and the nearest railhead (rail transport access point).
-
E.
distanceToRichmond
Indicates the measured distance between a given location or entity and the place named Richmond.
- 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_69f76eaeb69c8190b367df9330d6f6af |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1e32108190897356d6a7fed879 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.