Triple

T10126633
Position Surface form Disambiguated ID Type / Status
Subject Cosima Wagner E226231 entity
Predicate givenName P17 FINISHED
Object Cosima
Cosima is best known as the daughter of composer Franz Liszt and the wife of Richard Wagner, whose legacy she helped preserve and promote.
 E841517 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: Cosima | Statement: [Cosima Wagner, givenName, Cosima]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Cosima
Context triple: [Cosima Wagner, givenName, Cosima]
  • A. Cosima Niehaus
    Cosima Niehaus is a brilliant, dreadlocked evolutionary developmental biologist and one of the central clone characters in the science fiction TV series "Orphan Black."
  • B. Cecilia
    Cecilia is a feminine given name of Latin origin, traditionally associated with Saint Cecilia, the patron saint of music.
  • C. Cosima Shaw
    Cosima Shaw is a German-British actress known for her work in science fiction and drama, including prominent roles in television and film.
  • D. Gisela
    Gisela was a daughter of Charlemagne, the Frankish king and first Holy Roman Emperor, and a member of the Carolingian royal family.
  • E. Viviane
    Viviane is a legendary enchantress of Arthurian romance, often identified as the Lady of the Lake and known for her role in mentoring and imprisoning the wizard Merlin.
  • 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: Cosima
Triple: [Cosima Wagner, givenName, Cosima]
Generated description
Cosima is best known as the daughter of composer Franz Liszt and the wife of Richard Wagner, whose legacy she helped preserve and promote.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Cosima
Target entity description: Cosima is best known as the daughter of composer Franz Liszt and the wife of Richard Wagner, whose legacy she helped preserve and promote.
  • A. Cosima Niehaus
    Cosima Niehaus is a brilliant, dreadlocked evolutionary developmental biologist and one of the central clone characters in the science fiction TV series "Orphan Black."
  • B. Cecilia
    Cecilia is a feminine given name of Latin origin, traditionally associated with Saint Cecilia, the patron saint of music.
  • C. Cosima Shaw
    Cosima Shaw is a German-British actress known for her work in science fiction and drama, including prominent roles in television and film.
  • D. Gisela
    Gisela was a daughter of Charlemagne, the Frankish king and first Holy Roman Emperor, and a member of the Carolingian royal family.
  • E. Viviane
    Viviane is a legendary enchantress of Arthurian romance, often identified as the Lady of the Lake and known for her role in mentoring and imprisoning the wizard Merlin.
  • 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_69ca843057b48190a86730167f5d6b98 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cdd2eef7388190b95ffd02814f2d1f completed April 2, 2026, 2:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2cc69a5c88190ab7b108e1aab20ba completed April 5, 2026, 8:56 p.m.
NEDg Description generation batch_69d2cd90fb888190833ca68dd644860d completed April 5, 2026, 9:01 p.m.
NED2 Entity disambiguation (via description) batch_69d2ce02525881908a5394acb7967ba2 completed April 5, 2026, 9:02 p.m.
Created at: March 30, 2026, 9:05 p.m.