Triple

T3504147
Position Surface form Disambiguated ID Type / Status
Subject Somme E74035 entity
Predicate containsTown P847 FINISHED
Object Ham
Ham is a small town in the Somme department of northern France, known historically for its medieval fortress and strategic location.
 E363954 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: Ham | Statement: [Somme, containsTown, Ham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ham
Context triple: [Somme, containsTown, Ham]
  • A. Ham
    Ham is a suburban riverside district in southwest London, England, known for its historic houses, green spaces, and proximity to the River Thames.
  • B. HAM
    HAM is the IATA airport code for Hamburg Airport, the international airport serving the city of Hamburg, Germany.
  • C. HAM
    HAM is the standard abbreviation used for the Canadian Football League team, the Hamilton Tiger-Cats.
  • D. Ho
    Ho are an indigenous Adivasi community of eastern India, primarily inhabiting parts of Jharkhand and Odisha, known for their Austroasiatic Ho language and distinct cultural traditions.
  • E. Hap
    Hap is the nickname of Henry "Hap" Arnold, a pioneering U.S. Army Air Forces general and key architect of American air power during World War II.
  • 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: Ham
Triple: [Somme, containsTown, Ham]
Generated description
Ham is a small town in the Somme department of northern France, known historically for its medieval fortress and strategic location.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ham
Target entity description: Ham is a small town in the Somme department of northern France, known historically for its medieval fortress and strategic location.
  • A. Ham
    Ham is a suburban riverside district in southwest London, England, known for its historic houses, green spaces, and proximity to the River Thames.
  • B. HAM
    HAM is the IATA airport code for Hamburg Airport, the international airport serving the city of Hamburg, Germany.
  • C. HAM
    HAM is the standard abbreviation used for the Canadian Football League team, the Hamilton Tiger-Cats.
  • D. Ho
    Ho are an indigenous Adivasi community of eastern India, primarily inhabiting parts of Jharkhand and Odisha, known for their Austroasiatic Ho language and distinct cultural traditions.
  • E. Hap
    Hap is the nickname of Henry "Hap" Arnold, a pioneering U.S. Army Air Forces general and key architect of American air power during World War II.
  • 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_69ad85ce7a9c81909ddc5cf0cb67a6e3 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adbbf22b1c8190956141d8fb924210 completed March 8, 2026, 6:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69b373de0a34819096701e24409a08bb completed March 13, 2026, 2:18 a.m.
NEDg Description generation batch_69b377dfd2308190b2762715fa098260 completed March 13, 2026, 2:35 a.m.
NED2 Entity disambiguation (via description) batch_69b37850f18081908ee893dd4cedc183 completed March 13, 2026, 2:37 a.m.
Created at: March 8, 2026, 3:18 p.m.