Triple
T19099697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khanderao Gate |
E467496
|
entity |
| Predicate | formsAccessRouteTo |
P96775
|
FINISHED |
| Object | interior areas of Jhansi Fort |
—
|
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: interior areas of Jhansi Fort | Statement: [Khanderao Gate, formsAccessRouteTo, interior areas of Jhansi Fort]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formsAccessRouteTo Context triple: [Khanderao Gate, formsAccessRouteTo, interior areas of Jhansi Fort]
-
A.
hasAccessRouteTo
chosen
Indicates that one entity possesses a path, connection, or means of reaching or interacting with another entity.
-
B.
formsKeyRouteTo
Indicates that something serves as a primary or essential pathway or connection leading to another thing.
-
C.
routeTypeAccessed
Indicates that a particular type of route has been accessed or used in some context.
-
D.
isAccessRouteAround
Indicates that one entity serves as an access route that goes around or circumvents another entity.
-
E.
controlsRoute
Indicates that one entity has authority over or manages the path, course, or routing taken by another entity.
- 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e36d279081908aeb472cd740c302 |
completed | April 20, 2026, 8:27 a.m. |
| PD | Predicate disambiguation | batch_69e4b9ac41848190afd0f33b42cebe99 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:04 p.m.