Triple
T32003403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mumbai–Hyderabad line |
E817192
|
entity |
| Predicate | startCityRole |
P22794
|
FINISHED |
| Object | financial capital of India |
—
|
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: financial capital of India | Statement: [Mumbai–Hyderabad line, startCityRole, financial capital of India]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startCityRole Context triple: [Mumbai–Hyderabad line, startCityRole, financial capital of India]
-
A.
endpointCityRole
Indicates the role or function that a city plays as an endpoint within a route, connection, or network.
-
B.
startCity
chosen
Indicates the city where a journey, route, or transportation service begins.
-
C.
hasCityRole
Indicates that an entity holds or is assigned a specific role, function, or status within a particular city.
-
D.
focusCityRole
Indicates that a city serves a particular primary role or function within a broader geographic or organizational context.
-
E.
homeCityRole
Indicates that an entity holds or held a specific role, position, or function associated with their home city.
- 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_69f348f8ce388190ae84376b1f348f12 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69ff5b233e9c8190adc06cca0758986b |
completed | May 9, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69ff5a5682108190a006b23c4fcdcc7c |
completed | May 9, 2026, 4:01 p.m. |
Created at: May 1, 2026, 12:14 a.m.