Triple

T598926
Position Surface form Disambiguated ID Type / Status
Subject Theresa May E11449 entity
Predicate familyName P18 FINISHED
Object May
May is a common English surname borne by numerous individuals, including former UK Prime Minister Theresa May.
 E74874 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: May | Statement: [Theresa May, familyName, May]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: May
Context triple: [Theresa May, familyName, May]
  • A. April
    April is a spring month in the Gregorian calendar often associated with mild weather and the blooming of many flowers.
  • B. September
    September is the ninth month of the year in the Gregorian calendar, marking the transition from summer to autumn in the Northern Hemisphere and from winter to spring in the Southern Hemisphere.
  • C. November
    November is the eleventh month of the Gregorian calendar, associated in the United States with late autumn, Thanksgiving, and the height of the football season.
  • D. Nisan
    Nisan is the first month of the Hebrew religious year, traditionally associated with spring and the festival of Passover.
  • E. Maand
    Maand is a classical folk music style from Rajasthan, India, known for its expressive melodies and royal courtly associations.
  • 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: May
Triple: [Theresa May, familyName, May]
Generated description
May is a common English surname borne by numerous individuals, including former UK Prime Minister Theresa May.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: May
Target entity description: May is a common English surname borne by numerous individuals, including former UK Prime Minister Theresa May.
  • A. April
    April is a spring month in the Gregorian calendar often associated with mild weather and the blooming of many flowers.
  • B. September
    September is the ninth month of the year in the Gregorian calendar, marking the transition from summer to autumn in the Northern Hemisphere and from winter to spring in the Southern Hemisphere.
  • C. November
    November is the eleventh month of the Gregorian calendar, associated in the United States with late autumn, Thanksgiving, and the height of the football season.
  • D. Nisan
    Nisan is the first month of the Hebrew religious year, traditionally associated with spring and the festival of Passover.
  • E. Maand
    Maand is a classical folk music style from Rajasthan, India, known for its expressive melodies and royal courtly associations.
  • 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_69a4932779b881908688590d59c71900 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49d776c6c819081b41a9b55041cd5 completed March 1, 2026, 8:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69a51f36ab388190a418f6d4ffe91d66 completed March 2, 2026, 5:25 a.m.
NEDg Description generation batch_69a51fed5cf881908565dfb8c798807a completed March 2, 2026, 5:28 a.m.
NED2 Entity disambiguation (via description) batch_69a5206e05148190a1c8c65bad1a637a completed March 2, 2026, 5:30 a.m.
Created at: March 1, 2026, 7:35 p.m.