Triple

T23230792
Position Surface form Disambiguated ID Type / Status
Subject CEED E581147 entity
Predicate acronym P43 FINISHED
Object CEED NE NERFINISHED

How this triple was built (2 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: CEED | Statement: [CEED, acronym, CEED]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CEED
Context triple: [CEED, acronym, CEED]
  • A. CEED
    CEED is a research center focused on understanding the formation, evolution, and dynamic processes of the Earth.
  • B. CEED
    CEED (Common Entrance Examination for Design) is a national-level entrance exam in India that evaluates candidates’ aptitude for postgraduate studies in design at premier institutes like the IITs and IISc.
  • C. CHED
    CHED is the commonly used abbreviation for the Division of Chemical Education, a professional organization focused on advancing the teaching and learning of chemistry.
  • D. CED
    CED is an academic unit focused on the study and practice of environmental design, including fields such as architecture, landscape architecture, and urban planning.
  • E. CED
    CED (Capacitance Electronic Disc) is an obsolete analog video disc format developed by RCA that stored movies on grooved vinyl-like discs read by a stylus.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

Provenance (2 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_69e246043c48819089bae72c9a9c306c completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f19231ef908190a791b4967916a66f completed April 29, 2026, 5:08 a.m.
Created at: April 17, 2026, 4:09 p.m.