Triple

T7662840
Position Surface form Disambiguated ID Type / Status
Subject Ruth First E173549 entity
Predicate familyName P18 FINISHED
Object First
First is a surname most notably associated with Ruth First, a South African anti-apartheid activist, journalist, and scholar.
 E680052 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: First | Statement: [Ruth First, familyName, First]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: First
Context triple: [Ruth First, familyName, First]
  • A. FIRST
    FIRST (For Inspiration and Recognition of Science and Technology) is an international youth organization that runs robotics competitions and programs to inspire students’ interest and participation in science, technology, engineering, and math.
  • B. Unua
    Unua is an Oceanic language spoken by a small community in Vanuatu.
  • C. First of the First
    First of the First is the nickname of the 1st Battalion, 1st Marines, a storied infantry battalion of the United States Marine Corps known for its long combat history.
  • D. First Section
    First Section is the premier market tier of the Tokyo Stock Exchange, listing large, established companies that meet stringent financial and governance standards.
  • E. Up First
    Up First is NPR's daily morning news podcast that delivers a concise roundup of the day's top stories.
  • 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: First
Triple: [Ruth First, familyName, First]
Generated description
First is a surname most notably associated with Ruth First, a South African anti-apartheid activist, journalist, and scholar.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: First
Target entity description: First is a surname most notably associated with Ruth First, a South African anti-apartheid activist, journalist, and scholar.
  • A. FIRST
    FIRST (For Inspiration and Recognition of Science and Technology) is an international youth organization that runs robotics competitions and programs to inspire students’ interest and participation in science, technology, engineering, and math.
  • B. Unua
    Unua is an Oceanic language spoken by a small community in Vanuatu.
  • C. First of the First
    First of the First is the nickname of the 1st Battalion, 1st Marines, a storied infantry battalion of the United States Marine Corps known for its long combat history.
  • D. First Section
    First Section is the premier market tier of the Tokyo Stock Exchange, listing large, established companies that meet stringent financial and governance standards.
  • E. Up First
    Up First is NPR's daily morning news podcast that delivers a concise roundup of the day's top stories.
  • 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_69c69955517c819085bc715b96d304d2 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c701a74a2c81909f78ab2de7ce807c completed March 27, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c89b1aaef081908d1d181ea7c28c2f completed March 29, 2026, 3:23 a.m.
NEDg Description generation batch_69c89e177fd08190a6f3a70cf32365d9 completed March 29, 2026, 3:35 a.m.
NED2 Entity disambiguation (via description) batch_69c89e7328f4819088651b60e7af457d completed March 29, 2026, 3:37 a.m.
Created at: March 27, 2026, 3:59 p.m.