Triple
T27496277
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karrani (Karlani) Afghan tribe |
E694026
|
entity |
| Predicate | associatedRegionHistorically |
P13711
|
FINISHED |
| Object | Bengal |
—
|
NE NERFINISHED |
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: Bengal | Statement: [Karrani (Karlani) Afghan tribe, associatedRegionHistorically, Bengal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedRegionHistorically Context triple: [Karrani (Karlani) Afghan tribe, associatedRegionHistorically, Bengal]
-
A.
historicalRegion
Indicates that an entity is or was a geographically defined area recognized for its significance during a particular historical period.
-
B.
historicallyIncludedRegion
Indicates that one region was formerly part of, or contained within, another region during a past historical period.
-
C.
historicalRegionCode
Indicates that an entity is associated with a specific code identifying a historical region.
-
D.
historicalRegionCorrespondsTo
Indicates that a historical region matches or aligns with a specific region, territory, or administrative unit in terms of location, extent, or identity.
-
E.
historicalRegionAssociation
chosen
Indicates an association where an entity is or was located in, part of, or otherwise related to a specific historical region.
- 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_69ef538370888190b1ddf53bb4831188 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_6a000014497c819088d5cda3977522dd |
completed | May 10, 2026, 3:48 a.m. |
| PD | Predicate disambiguation | batch_69ffff9a52b08190be1024e0fb6fe661 |
completed | May 10, 2026, 3:46 a.m. |
Created at: April 27, 2026, 1:08 p.m.