Triple

T23231953
Position Surface form Disambiguated ID Type / Status
Subject Black Spring E581179 entity
Predicate hasPart P35 FINISHED
Object “Mara-Marignan”
“Mara-Marignan” is a component or section of the larger work *Black Spring*, likely a distinct chapter or piece within that literary collection.
 E1576652 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: “Mara-Marignan” | Statement: [Black Spring, hasPart, “Mara-Marignan”]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: “Mara-Marignan”
Context triple: [Black Spring, hasPart, “Mara-Marignan”]
  • A. Mareil-Marly
    Mareil-Marly is a small suburban commune in the Yvelines department of north-central France, located west of Paris.
  • B. Marcané
    Marcané is a locality within Cueto Municipality in Holguín Province, Cuba, known primarily as a small rural community.
  • C. Marsannay
    Marsannay is a Burgundy wine appellation at the northern end of the Côte de Nuits, known for producing red, white, and rosé wines.
  • D. Marsan
    Marsan is a small rural settlement located within the Qakh District of Azerbaijan.
  • E. Marsan
    Marsan is a French surname borne by various notable individuals, including actors and public figures.
  • 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: “Mara-Marignan”
Triple: [Black Spring, hasPart, “Mara-Marignan”]
Generated description
“Mara-Marignan” is a component or section of the larger work *Black Spring*, likely a distinct chapter or piece within that literary collection.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: “Mara-Marignan”
Target entity description: “Mara-Marignan” is a component or section of the larger work *Black Spring*, likely a distinct chapter or piece within that literary collection.
  • A. Mareil-Marly
    Mareil-Marly is a small suburban commune in the Yvelines department of north-central France, located west of Paris.
  • B. Marcané
    Marcané is a locality within Cueto Municipality in Holguín Province, Cuba, known primarily as a small rural community.
  • C. Marsannay
    Marsannay is a Burgundy wine appellation at the northern end of the Côte de Nuits, known for producing red, white, and rosé wines.
  • D. Marsan
    Marsan is a small rural settlement located within the Qakh District of Azerbaijan.
  • E. Marsan
    Marsan is a French surname borne by various notable individuals, including actors and public figures.
  • 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_69e246043c48819089bae72c9a9c306c completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f1923325a08190a529da687de53489 completed April 29, 2026, 5:08 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c3f577f5c8190a8c8bdf9bd5305f5 completed May 19, 2026, 10:45 a.m.
NEDg Description generation batch_6a0c4008c4a881908ad49e733b549036 completed May 19, 2026, 10:48 a.m.
NED2 Entity disambiguation (via description) batch_6a0c40c6562481908689eca2a4997115 completed May 19, 2026, 10:51 a.m.
Created at: April 17, 2026, 4:09 p.m.