Triple

T6390856
Position Surface form Disambiguated ID Type / Status
Subject Musselburgh E143821 entity
Predicate hasMotto P42 FINISHED
Object Honestas
Honestas is the Latin motto of Musselburgh, traditionally interpreted as emphasizing honesty and integrity.
E591206 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: Honestas | Statement: [Musselburgh, hasMotto, Honestas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Honestas
Context triple: [Musselburgh, hasMotto, Honestas]
  • A. Fidelitas et Integritas
    Fidelitas et Integritas is the Latin school motto of Choate Rosemary Hall, expressing the values of loyalty and integrity.
  • B. Honor y Lealtad
    Honor y Lealtad is the official motto of Chile’s investigative police force, encapsulating its core values of integrity and loyalty in law enforcement service.
  • C. Veritas et Virtus
    Veritas et Virtus is the Latin school motto of Westminster City School, expressing the ideals of truth and virtue.
  • D. Valor, Lealdade e Mérito
    Valor, Lealdade e Mérito is the Portuguese-language motto of the Order of the Tower and Sword, expressing the ideals of courage, loyalty, and merit.
  • E. The Sincerity
    The Sincerity is an English rendering of Surah Al-Ikhlas, a short but central chapter of the Qur’an that emphasizes the absolute oneness and uniqueness of God.
  • 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: Honestas
Triple: [Musselburgh, hasMotto, Honestas]
Generated description
Honestas is the Latin motto of Musselburgh, traditionally interpreted as emphasizing honesty and integrity.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Honestas
Target entity description: Honestas is the Latin motto of Musselburgh, traditionally interpreted as emphasizing honesty and integrity.
  • A. Fidelitas et Integritas
    Fidelitas et Integritas is the Latin school motto of Choate Rosemary Hall, expressing the values of loyalty and integrity.
  • B. Honor y Lealtad
    Honor y Lealtad is the official motto of Chile’s investigative police force, encapsulating its core values of integrity and loyalty in law enforcement service.
  • C. Veritas et Virtus
    Veritas et Virtus is the Latin school motto of Westminster City School, expressing the ideals of truth and virtue.
  • D. Valor, Lealdade e Mérito
    Valor, Lealdade e Mérito is the Portuguese-language motto of the Order of the Tower and Sword, expressing the ideals of courage, loyalty, and merit.
  • E. The Sincerity
    The Sincerity is an English rendering of Surah Al-Ikhlas, a short but central chapter of the Qur’an that emphasizes the absolute oneness and uniqueness of God.
  • 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_69c008db906c819096f3597d55d95432 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0687c7fdc819099cbbb937dec215e completed March 22, 2026, 10:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6388b02888190989623c658469a5a completed March 27, 2026, 7:58 a.m.
NEDg Description generation batch_69c63c71ac188190ad7912d2e6a68af8 completed March 27, 2026, 8:14 a.m.
NED2 Entity disambiguation (via description) batch_69c63cdf225c8190b26a23496d0acc1a completed March 27, 2026, 8:16 a.m.
Created at: March 22, 2026, 4:34 p.m.