Triple
T15884936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morava river system |
E385167
|
entity |
| Predicate | majorRiver |
P165
|
FINISHED |
| Object | Pusta Reka |
E1174066
|
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: Pusta Reka | Statement: [Morava river system, majorRiver, Pusta Reka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pusta Reka Context triple: [Morava river system, majorRiver, Pusta Reka]
-
A.
Pusta Reka
chosen
Pusta Reka is a river in southern Serbia that flows through a rural valley before joining the South Morava.
-
B.
Shastina
Shastina is a prominent satellite cone and secondary peak on the western flank of California’s Mount Shasta, formed by later volcanic activity.
-
C.
Gogra
Gogra is an alternative name for Kauriala, a locality whose identity is primarily tied to this regional designation.
-
D.
Goghat
Goghat is a town in West Bengal, India, known primarily as a rural administrative and agricultural center within the Hooghly region.
-
E.
Vishkanya
Vishkanya is a 1991 Indian Hindi-language horror film known for its supernatural revenge plot and early appearance of actress Riya Sen.
- 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_69d86da5b800819083a31be937d738b0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1561997bc8190a40e7d68defbbddd |
completed | April 16, 2026, 9:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa95651f88190a9aac72a667b999f |
completed | May 9, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:51 a.m.