Triple

T4938159
Position Surface form Disambiguated ID Type / Status
Subject Bay of Kotor E110862 entity
Predicate hasIsland P970 FINISHED
Object Mamula
Mamula is a small fortified island in the Adriatic Sea off the coast of Montenegro, known for its 19th-century Austro-Hungarian fortress and former use as a prison.
 E481733 NE FINISHED

How this triple was built (4 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: Mamula | Statement: [Bay of Kotor, hasIsland, Mamula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mamula
Context triple: [Bay of Kotor, hasIsland, Mamula]
  • A. Mamati
    Mamati is a village in western Georgia notable as the birthplace of former Soviet and Georgian politician Eduard Shevardnadze.
  • B. Manda
    Manda is a lesser-known Dravidian language spoken by tribal communities in parts of eastern India, particularly in Odisha.
  • C. Mongibello
    Mongibello is a traditional name used in Italian and Sicilian contexts to refer to Mount Etna, the large active volcano on the east coast of Sicily.
  • D. Mēmele
    Mēmele is a river in the Baltic region that serves as one of the headwaters forming Latvia’s Lielupe River.
  • E. Myaso
    Myaso is a colloquial nickname used by fans and rivals to refer to the Russian football club Spartak Moscow, reflecting its historical association with the meat industry.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mamula
Triple: [Bay of Kotor, hasIsland, Mamula]
Generated description
Mamula is a small fortified island in the Adriatic Sea off the coast of Montenegro, known for its 19th-century Austro-Hungarian fortress and former use as a prison.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mamula
Target entity description: Mamula is a small fortified island in the Adriatic Sea off the coast of Montenegro, known for its 19th-century Austro-Hungarian fortress and former use as a prison.
  • A. Mamati
    Mamati is a village in western Georgia notable as the birthplace of former Soviet and Georgian politician Eduard Shevardnadze.
  • B. Manda
    Manda is a lesser-known Dravidian language spoken by tribal communities in parts of eastern India, particularly in Odisha.
  • C. Mongibello
    Mongibello is a traditional name used in Italian and Sicilian contexts to refer to Mount Etna, the large active volcano on the east coast of Sicily.
  • D. Mēmele
    Mēmele is a river in the Baltic region that serves as one of the headwaters forming Latvia’s Lielupe River.
  • E. Myaso
    Myaso is a colloquial nickname used by fans and rivals to refer to the Russian football club Spartak Moscow, reflecting its historical association with the meat industry.
  • F. None of above. chosen

Provenance (5 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_69bd4415eee08190bdce70276e56a5b4 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd70872270819080769dad972681ef completed March 20, 2026, 4:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69be77bcb8d881908d393223bdea145a completed March 21, 2026, 10:49 a.m.
NEDg Description generation batch_69be78747f3881908afe9cf276216bc5 completed March 21, 2026, 10:52 a.m.
NED2 Entity disambiguation (via description) batch_69be78d03aec81909a2470306ba90cb0 completed March 21, 2026, 10:54 a.m.
Created at: March 20, 2026, 1:31 p.m.