Triple

T12430614
Position Surface form Disambiguated ID Type / Status
Subject Jounieh E297018 entity
Predicate near P350 FINISHED
Object Harissa
Harissa is a hilltop pilgrimage site in Lebanon famous for its towering statue and shrine of Our Lady of Lebanon overlooking the Bay of Jounieh.
 E981315 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: Harissa | Statement: [Jounieh, near, Harissa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Harissa
Context triple: [Jounieh, near, Harissa]
  • A. Segeda
    Segeda was a prominent ancient Celtiberian city in what is now northeastern Spain, known for its role in the Celtiberian Wars against Rome.
  • B. Mustard
    Mustard is an American record producer and DJ known for his minimalist, club-oriented West Coast hip hop sound and numerous chart-topping collaborations.
  • C. baba ghanoush
    Baba ghanoush is a Middle Eastern dip made from roasted eggplant blended with tahini, lemon juice, garlic, and seasonings.
  • D. Pimentón de la Vera
    Pimentón de la Vera is a smoked Spanish paprika with protected designation of origin, renowned for its intense flavor and deep red color.
  • E. Kousba
    Kousba is a town in northern Lebanon located in the Koura District, known for its olive groves and traditional Lebanese rural character.
  • 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: Harissa
Triple: [Jounieh, near, Harissa]
Generated description
Harissa is a hilltop pilgrimage site in Lebanon famous for its towering statue and shrine of Our Lady of Lebanon overlooking the Bay of Jounieh.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Harissa
Target entity description: Harissa is a hilltop pilgrimage site in Lebanon famous for its towering statue and shrine of Our Lady of Lebanon overlooking the Bay of Jounieh.
  • A. Segeda
    Segeda was a prominent ancient Celtiberian city in what is now northeastern Spain, known for its role in the Celtiberian Wars against Rome.
  • B. Mustard
    Mustard is an American record producer and DJ known for his minimalist, club-oriented West Coast hip hop sound and numerous chart-topping collaborations.
  • C. baba ghanoush
    Baba ghanoush is a Middle Eastern dip made from roasted eggplant blended with tahini, lemon juice, garlic, and seasonings.
  • D. Pimentón de la Vera
    Pimentón de la Vera is a smoked Spanish paprika with protected designation of origin, renowned for its intense flavor and deep red color.
  • E. Kousba
    Kousba is a town in northern Lebanon located in the Koura District, known for its olive groves and traditional Lebanese rural character.
  • 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_69d6ada0640c81908c061d7fb3d47786 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d7f2fd08190ab959742dbd8f9c0 completed April 10, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6349b075c8190b77cd51bc45be8ef completed May 2, 2026, 5:30 p.m.
NEDg Description generation batch_69f636d0254481909147381502671ac0 completed May 2, 2026, 5:39 p.m.
NED2 Entity disambiguation (via description) batch_69f637902e7081909ce053142f7c1871 completed May 2, 2026, 5:42 p.m.
Created at: April 8, 2026, 9:55 p.m.