Triple

T12046117
Position Surface form Disambiguated ID Type / Status
Subject Zarephath E286790 entity
Predicate nameVariant P744 FINISHED
Object Sarepta
Sarepta is an ancient Phoenician coastal town, known from the Bible as the place where the prophet Elijah stayed with a widow during a severe famine.
 E961921 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: Sarepta | Statement: [Zarephath, nameVariant, Sarepta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sarepta
Context triple: [Zarephath, nameVariant, Sarepta]
  • A. Joubbé
    Joubbé is a locality in Lebanon that forms part of the pastoral territory served by the Maronite Catholic Eparchy of Joubbé, Sarba and Jounieh.
  • B. Hurler
    Hurler is a wooden roller coaster at the Carowinds amusement park known for its high-speed, rough-and-tumble ride experience.
  • C. Hipple
    Hipple is the birth surname of American film and television actor Hugh Marlowe.
  • D. Andermann
    Andermann is a German-language surname borne by individuals such as Hermine Andermann.
  • E. Gotaas-Larsen
    Gotaas-Larsen was a Norwegian shipping company and maritime enterprise that played a key role in the early development of modern cruise operations.
  • 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: Sarepta
Triple: [Zarephath, nameVariant, Sarepta]
Generated description
Sarepta is an ancient Phoenician coastal town, known from the Bible as the place where the prophet Elijah stayed with a widow during a severe famine.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sarepta
Target entity description: Sarepta is an ancient Phoenician coastal town, known from the Bible as the place where the prophet Elijah stayed with a widow during a severe famine.
  • A. Joubbé
    Joubbé is a locality in Lebanon that forms part of the pastoral territory served by the Maronite Catholic Eparchy of Joubbé, Sarba and Jounieh.
  • B. Hurler
    Hurler is a wooden roller coaster at the Carowinds amusement park known for its high-speed, rough-and-tumble ride experience.
  • C. Hipple
    Hipple is the birth surname of American film and television actor Hugh Marlowe.
  • D. Andermann
    Andermann is a German-language surname borne by individuals such as Hermine Andermann.
  • E. Gotaas-Larsen
    Gotaas-Larsen was a Norwegian shipping company and maritime enterprise that played a key role in the early development of modern cruise operations.
  • 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_69d6ab4780948190bdb9f7620c2ac27e completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d9041fe3b0819094b82a6b17ac59c3 completed April 10, 2026, 2:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69f49db574bc8190a0f2f858a2ff788d completed May 1, 2026, 12:33 p.m.
NEDg Description generation batch_69f53d95d4fc8190b5f4e460646bec2a completed May 1, 2026, 11:56 p.m.
NED2 Entity disambiguation (via description) batch_69f564d2b4348190abf2d09ae00aea37 completed May 2, 2026, 2:43 a.m.
Created at: April 8, 2026, 9:47 p.m.