Triple
T18975973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duronto Express |
E464296
|
entity |
| Predicate | categoryWithinIndianRailways |
P107548
|
FINISHED |
| Object | premium express |
—
|
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: premium express | Statement: [Duronto Express, categoryWithinIndianRailways, premium express]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: categoryWithinIndianRailways Context triple: [Duronto Express, categoryWithinIndianRailways, premium express]
-
A.
railwayStationCategory
Indicates the classification or type category assigned to a railway station within a rail network or system.
-
B.
trainsCategory
Indicates that one entity is a category or type under which the other entity is trained or classified.
-
C.
railwayClass
Indicates the specific classification or category assigned to a railway or railway service within a defined system.
-
D.
trainCategory
chosen
Indicates the classification or type of a train within a railway system (e.g., express, regional, freight).
-
E.
railServiceType
Indicates the specific category or type of rail service that applies to the relationship between the involved entities (e.g., local, express, freight).
- 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_69d8dd008af48190a97ff1c6488edf1b |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d61f96c88190b9a25158e0b012ca |
completed | April 20, 2026, 7:30 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f437648190b85650dae8885d48 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, noon