Triple
T24014521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | historicEast–WestRailCorridor |
E594631
|
entity |
| Predicate | transcontinentalDirection |
P154871
|
FINISHED |
| Object | east–west |
—
|
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: east–west | Statement: [historicEast–WestRailCorridor, transcontinentalDirection, east–west]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transcontinentalDirection Context triple: [historicEast–WestRailCorridor, transcontinentalDirection, east–west]
-
A.
transcontinentalRegion
Indicates a region that spans or extends across more than one continent.
-
B.
mainTranscontinentalConnection
Indicates that something serves as the primary route or link connecting regions or networks that span across an entire continent.
-
C.
partOfTranscontinentalRegion
Indicates that a region is a constituent part of a larger transcontinental region that spans more than one continent.
-
D.
crossesContinent
Indicates that one entity traverses from one side of a continent to the other, passing across its landmass.
-
E.
continentConnection
Indicates a relationship where two or more entities are linked by being located on, spanning, or otherwise associated with the same continent or connected continents.
- 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_69e288bc8f608190ac4af29f0bd1c744 |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d5a0aa408190a27fca07777cda05 |
completed | April 29, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_69f17639d23c8190bed93434e2f9230a |
completed | April 29, 2026, 3:08 a.m. |
| PDg | Predicate description generation | batch_69f17c28b684819084eea522126463f8 |
completed | April 29, 2026, 3:34 a.m. |
Created at: April 17, 2026, 9:42 p.m.