Triple
T27496163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanda |
E694023
|
entity |
| Predicate | countryDuringHeyday |
P41268
|
FINISHED |
| Object | Bengal Sultanate |
—
|
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 Sultanate | Statement: [Tanda, countryDuringHeyday, Bengal Sultanate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryDuringHeyday Context triple: [Tanda, countryDuringHeyday, Bengal Sultanate]
-
A.
countryDuring
chosen
Indicates that one entity exists, occurs, or is valid within the temporal span during which the other entity is recognized as a specific country.
-
B.
countryDuringLaterPeriod
Indicates that an entity served as the country associated with another entity during a specified later time period.
-
C.
countryAtTheTime
Indicates that an entity is associated with a specific country as it existed at a particular point in time.
-
D.
countryInThePast
Indicates that an entity was recognized as a country during some period in the past, but is not necessarily a country in the present.
-
E.
country1
Indicates that the subject entity is a country (or represents a country) in the given context.
- 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_69fd4d1854988190be093b103a681798 |
completed | May 8, 2026, 2:40 a.m. |
| PD | Predicate disambiguation | batch_69fd4c8d1a188190897c24527337814a |
completed | May 8, 2026, 2:38 a.m. |
Created at: April 27, 2026, 1:08 p.m.