Triple
T31661835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Canterbury provincial railways |
E808022
|
entity |
| Predicate | trackGaugeChange |
P120346
|
FINISHED |
| Object | converted to 3 ft 6 in gauge |
—
|
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: converted to 3 ft 6 in gauge | Statement: [Canterbury provincial railways, trackGaugeChange, converted to 3 ft 6 in gauge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trackGaugeChange Context triple: [Canterbury provincial railways, trackGaugeChange, converted to 3 ft 6 in gauge]
-
A.
trackGauge
Indicates the distance between the inner faces of the rails in a railway track system.
-
B.
trackGaugeOptions
Indicates the available or applicable gauge (measurement) configurations that can be used for a given track.
-
C.
trackGaugeUnit
Indicates the unit of measurement used to express the gauge (width) of a track.
-
D.
formerTrackGauge
chosen
Indicates that an entity previously had a specified track gauge, which has since been changed or is no longer in use.
-
E.
gaugeChangeFunction
Indicates a function that specifies how a gauge’s value changes in response to varying inputs or conditions.
- 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_69f348dbeef4819080b446a7feb6340b |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f7221dc9a88190bb8194fcc29c42bc |
completed | May 3, 2026, 10:23 a.m. |
| PD | Predicate disambiguation | batch_69f72153a9188190b02adc84e1be4af8 |
completed | May 3, 2026, 10:20 a.m. |
Created at: April 30, 2026, 10:57 p.m.