Triple

T19962832
Position Surface form Disambiguated ID Type / Status
Subject Gerda Taro E479857 entity
Predicate givenName P17 FINISHED
Object Gerta
Gerta is the given name of Gerda Taro, a pioneering war photographer known for her coverage of the Spanish Civil War.
 E1404766 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: Gerta | Statement: [Gerda Taro, givenName, Gerta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gerta
Context triple: [Gerda Taro, givenName, Gerta]
  • A. Geira
    Geira was a Wendish princess who became the first wife of Olaf Tryggvason, the future king of Norway.
  • B. Egau
    Egau is a small river in the German state of Baden-Württemberg that flows through the district of Heidenheim.
  • C. Gornal
    Gornal is a suburban area and community within the West Midlands region of England, historically associated with coal mining and the Black Country.
  • D. Grua
    Grua is a small village in Lunner Municipality in Viken county, Norway, known as a local residential community in the Hadeland region.
  • E. Nigrán
    Nigrán is a coastal municipality in the province of Pontevedra, in the autonomous community of Galicia in northwestern Spain.
  • 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: Gerta
Triple: [Gerda Taro, givenName, Gerta]
Generated description
Gerta is the given name of Gerda Taro, a pioneering war photographer known for her coverage of the Spanish Civil War.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gerta
Target entity description: Gerta is the given name of Gerda Taro, a pioneering war photographer known for her coverage of the Spanish Civil War.
  • A. Geira
    Geira was a Wendish princess who became the first wife of Olaf Tryggvason, the future king of Norway.
  • B. Egau
    Egau is a small river in the German state of Baden-Württemberg that flows through the district of Heidenheim.
  • C. Gornal
    Gornal is a suburban area and community within the West Midlands region of England, historically associated with coal mining and the Black Country.
  • D. Grua
    Grua is a small village in Lunner Municipality in Viken county, Norway, known as a local residential community in the Hadeland region.
  • E. Nigrán
    Nigrán is a coastal municipality in the province of Pontevedra, in the autonomous community of Galicia in northwestern Spain.
  • 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_69d8e523c19881909f9197037200dde6 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65af51b4c81909ba156a489cbc551 completed April 20, 2026, 4:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07fdcece808190ab94df038b659b44 completed May 16, 2026, 5:17 a.m.
NEDg Description generation batch_6a07fe72f47c8190b63c6f528656329e completed May 16, 2026, 5:19 a.m.
NED2 Entity disambiguation (via description) batch_6a080261c6f88190a2ede168aab944b6 completed May 16, 2026, 5:36 a.m.
Created at: April 10, 2026, 1:54 p.m.