Triple
T3207777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shahrisabz |
E67205
|
entity |
| Predicate | historicalRegion |
P915
|
FINISHED |
| Object | Mawarannahr |
E67423
|
NE 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: Mawarannahr | Statement: [Shahrisabz, historicalRegion, Mawarannahr]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mawarannahr Context triple: [Shahrisabz, historicalRegion, Mawarannahr]
-
A.
Azania
Azania is a name used by some African liberation movements and activists to refer to a decolonized, non-apartheid South Africa.
-
B.
Khorasan
chosen
Khorasan is a historical region in northeastern Iran and surrounding areas that served as a major cultural and political center in various Persian and Islamic empires.
-
C.
Negaraku
Negaraku is the national anthem of Malaysia, symbolizing the country's sovereignty and unity.
-
D.
Karas Region
Karas Region is the southernmost administrative region of Namibia, known for its arid landscapes, desert scenery, and coastal towns along the Atlantic Ocean.
-
E.
Kosraean
Kosraean is an Austronesian language spoken primarily on the Micronesian island of Kosrae in the Federated States of Micronesia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad858ac36c81909962589cd277d6e2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaa58340881908347d772cfa0ac4c |
completed | March 8, 2026, 4:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b24bd0fcac8190a35690a109280702 |
completed | March 12, 2026, 5:14 a.m. |
Created at: March 8, 2026, 3:07 p.m.