Triple

T1052355
Position Surface form Disambiguated ID Type / Status
Subject Carthage E22727 entity
Predicate foundingLegendFeatures P5394 FINISHED
Object Elissa
Elissa, also known as Dido, is the legendary Phoenician princess who founded the ancient city of Carthage and became its first queen.
E121100 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: Elissa | Statement: [Carthage, foundingLegendFeatures, Elissa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elissa
Context triple: [Carthage, foundingLegendFeatures, Elissa]
  • A. Elissa Leonard
    Elissa Leonard is an American filmmaker and producer known for her work in documentary and independent film, as well as for being married to Federal Reserve Chair Jerome H. Powell.
  • B. Mya
    Mya is a central female character in the romantic comedy film "Think Like a Man," known for following Steve Harvey’s dating advice as she navigates modern relationships.
  • C. Rumi Carter
    Rumi Carter is one of the twin children of American music icons Beyoncé and Jay-Z, known primarily for her high-profile celebrity parentage.
  • D. Nelly Malek
    Nelly Malek is best known as the mother of Academy Award–winning actor Rami Malek.
  • E. Elisa
    Elisa is a feminine given name of Hebrew origin, often considered a short form of Elisabeth and used in various languages including Italian, Spanish, and French.
  • 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: Elissa
Triple: [Carthage, foundingLegendFeatures, Elissa]
Generated description
Elissa, also known as Dido, is the legendary Phoenician princess who founded the ancient city of Carthage and became its first queen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Elissa
Target entity description: Elissa, also known as Dido, is the legendary Phoenician princess who founded the ancient city of Carthage and became its first queen.
  • A. Elissa Leonard
    Elissa Leonard is an American filmmaker and producer known for her work in documentary and independent film, as well as for being married to Federal Reserve Chair Jerome H. Powell.
  • B. Mya
    Mya is a central female character in the romantic comedy film "Think Like a Man," known for following Steve Harvey’s dating advice as she navigates modern relationships.
  • C. Rumi Carter
    Rumi Carter is one of the twin children of American music icons Beyoncé and Jay-Z, known primarily for her high-profile celebrity parentage.
  • D. Nelly Malek
    Nelly Malek is best known as the mother of Academy Award–winning actor Rami Malek.
  • E. Elisa
    Elisa is a feminine given name of Hebrew origin, often considered a short form of Elisabeth and used in various languages including Italian, Spanish, and French.
  • 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_69a493da02e081908c13ff5e02a0fe7a completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4bb7320f88190a8428946541df157 completed March 1, 2026, 10:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac3bcf04448190af136ca4f037547b completed March 7, 2026, 2:53 p.m.
NEDg Description generation batch_69ac3c9a92008190a6336626faed36bd completed March 7, 2026, 2:56 p.m.
NED2 Entity disambiguation (via description) batch_69ac3d0fcdb88190b4c5e5ddf41e2716 completed March 7, 2026, 2:58 p.m.
Created at: March 1, 2026, 7:42 p.m.