Triple
T3328942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castlefield Viaduct |
E69986
|
entity |
| Predicate | transportModeServedHistorically |
P31374
|
FINISHED |
| Object | rail |
—
|
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: rail | Statement: [Castlefield Viaduct, transportModeServedHistorically, rail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transportModeServedHistorically Context triple: [Castlefield Viaduct, transportModeServedHistorically, rail]
-
A.
passesUsedForTransportation
Indicates that the passes are utilized as a means or instrument for transporting people or goods.
-
B.
transportModeAccess
Indicates that one entity has the ability or permission to use, reach, or be served by a particular mode of transportation.
-
C.
hasPublicTransportUsage
Indicates that an entity makes use of, or is associated with the use of, public transportation services.
-
D.
hasTransportHistory
chosen
Indicates that there exists a record or sequence of past transportation-related events or movements associated with an entity.
-
E.
transportModeIntegration
Indicates that different modes of transportation are coordinated or combined to enable seamless or efficient movement within a journey or transport system.
- 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_69ad85a1829881908942c14075644d0d |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb1708b908190bc5c4122623d9b77 |
completed | March 8, 2026, 5:27 p.m. |
| PD | Predicate disambiguation | batch_69ada42a19348190a3862ce02451f4aa |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:12 p.m.