Triple

T2829227
Position Surface form Disambiguated ID Type / Status
Subject Battle of Uman E62195 entity
Predicate alsoKnownAs P39 FINISHED
Object Uman pocket
Uman pocket is the name given to the large encirclement and destruction of Soviet forces by the German Army during the Battle of Uman in World War II.
E301247 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: Uman pocket | Statement: [Battle of Uman, alsoKnownAs, Uman pocket]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Uman pocket
Context triple: [Battle of Uman, alsoKnownAs, Uman pocket]
  • A. Pegu
    Pegu is an important historical city in Lower Myanmar that once served as the political and cultural center of the Mon people and a major hub of regional trade and Buddhism.
  • B. Pijin
    Pijin is an English-based creole language widely used as a lingua franca in the Solomon Islands.
  • C. Pearic
    Pearic is a small branch of Austroasiatic languages spoken by indigenous Pearic peoples in parts of Cambodia and Thailand.
  • D. Pileni
    Pileni is a small Polynesian outlier island community in the Solomon Islands, known for its Polynesian culture and language despite being located within Melanesia.
  • E. Pila
    Pila is a popular ski resort village in Italy’s Aosta Valley, known for its scenic Alpine slopes and views of major peaks like Mont Blanc and the Matterhorn.
  • 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: Uman pocket
Triple: [Battle of Uman, alsoKnownAs, Uman pocket]
Generated description
Uman pocket is the name given to the large encirclement and destruction of Soviet forces by the German Army during the Battle of Uman in World War II.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Uman pocket
Target entity description: Uman pocket is the name given to the large encirclement and destruction of Soviet forces by the German Army during the Battle of Uman in World War II.
  • A. Pegu
    Pegu is an important historical city in Lower Myanmar that once served as the political and cultural center of the Mon people and a major hub of regional trade and Buddhism.
  • B. Pijin
    Pijin is an English-based creole language widely used as a lingua franca in the Solomon Islands.
  • C. Pearic
    Pearic is a small branch of Austroasiatic languages spoken by indigenous Pearic peoples in parts of Cambodia and Thailand.
  • D. Pileni
    Pileni is a small Polynesian outlier island community in the Solomon Islands, known for its Polynesian culture and language despite being located within Melanesia.
  • E. Pila
    Pila is a popular ski resort village in Italy’s Aosta Valley, known for its scenic Alpine slopes and views of major peaks like Mont Blanc and the Matterhorn.
  • 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_69ab4c3c39188190955b9c49d98463d8 completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abde97168c8190b31122b2ad9fdebf completed March 7, 2026, 8:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69afceb4f3ec8190987afb7a2ac302e2 completed March 10, 2026, 7:56 a.m.
NEDg Description generation batch_69afcf46a4e88190907ca735a1745c79 completed March 10, 2026, 7:59 a.m.
NED2 Entity disambiguation (via description) batch_69afcff778748190978e7d306e0d1ce1 completed March 10, 2026, 8:01 a.m.
Created at: March 6, 2026, 10:01 p.m.