Triple

T2757053
Position Surface form Disambiguated ID Type / Status
Subject Louis Bernstein E61124 entity
Predicate notableWork P4 FINISHED
Object Mass
Mass is a 1971 theatre piece for singers, players, and dancers composed by Leonard Bernstein that blends classical, rock, jazz, and Broadway styles in a dramatic setting of the Roman Catholic Mass.
E40108 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: Mass | Statement: [Louis Bernstein, notableWork, Mass]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mass
Context triple: [Louis Bernstein, notableWork, Mass]
  • A. Massa
    Massa is a historic city in northwestern Tuscany, Italy, known for its marble industry and proximity to the Apuan Alps and the Tyrrhenian coast.
  • B. Massa
    Massa is a biblical figure listed among the descendants of Ishmael in the Hebrew Bible.
  • C. Manyika
    Manyika is a major dialect of the Shona language spoken primarily in eastern Zimbabwe and adjacent areas of Mozambique.
  • D. Mahas
    Mahas is an alternative name for the Nobiin language, a Nubian language spoken primarily along the Nile in southern Egypt and northern Sudan.
  • E. Masistes
    Masistes was a Persian prince of the Achaemenid dynasty, known as a son of King Darius I and a figure in the political and familial intrigues of Xerxes I’s reign.
  • 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: Mass
Triple: [Louis Bernstein, notableWork, Mass]
Generated description
Mass is a 1971 theatre piece for singers, players, and dancers composed by Leonard Bernstein that blends classical, rock, jazz, and Broadway styles in a dramatic setting of the Roman Catholic Mass.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mass
Target entity description: Mass is a 1971 theatre piece for singers, players, and dancers composed by Leonard Bernstein that blends classical, rock, jazz, and Broadway styles in a dramatic setting of the Roman Catholic Mass.
  • A. Mass chosen
    Mass is a large-scale theatrical work by Leonard Bernstein that blends elements of classical music, musical theater, and religious liturgy to explore themes of faith and doubt.
  • B. Massa
    Massa is a historic city in northwestern Tuscany, Italy, known for its marble industry and proximity to the Apuan Alps and the Tyrrhenian coast.
  • C. Massa
    Massa is a biblical figure listed among the descendants of Ishmael in the Hebrew Bible.
  • D. Manyika
    Manyika is a major dialect of the Shona language spoken primarily in eastern Zimbabwe and adjacent areas of Mozambique.
  • E. Mahas
    Mahas is an alternative name for the Nobiin language, a Nubian language spoken primarily along the Nile in southern Egypt and northern Sudan.
  • F. None of above.

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_69ab4b7a85bc819094a349b84beb1f2c completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdb8a292c8190ab3982434805241a completed March 7, 2026, 8:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69afbbdf650c8190baa020143b51f94b completed March 10, 2026, 6:36 a.m.
NEDg Description generation batch_69afbc67c39c8190b5932c0e23595f64 completed March 10, 2026, 6:38 a.m.
NED2 Entity disambiguation (via description) batch_69afbd2d8a2c8190896a9154ebbd8bab completed March 10, 2026, 6:41 a.m.
Created at: March 6, 2026, 9:56 p.m.