Triple

T23300459
Position Surface form Disambiguated ID Type / Status
Subject Ceylon Civil Service E590287 entity
Predicate shortName P43 FINISHED
Object CCS 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: CCS | Statement: [Ceylon Civil Service, shortName, CCS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CCS
Context triple: [Ceylon Civil Service, shortName, CCS]
  • A. CCS
    CCS (ACM Conference on Computer and Communications Security) is a premier annual research conference focusing on cutting-edge topics in information security and privacy.
  • B. CCS
    CCS is the commonly used abbreviation for the Central Coast Section, a regional governing body for high school athletics in California.
  • C. CCS chosen
    CCS is the abbreviated name for the Ceylon Civil Service, the former elite administrative service of British Ceylon (now Sri Lanka).
  • D. CCS
    CCS is a public school district serving Cabarrus County in North Carolina, providing K–12 education across multiple schools in the region.
  • E. CCS
    The CCS is a high-level Indian government body that makes key decisions on national security, defense, and strategic affairs.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69e25d1c0ecc8190a355aa229f06d0e0 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f196d2b5dc819084b4d0290184de62 completed April 29, 2026, 5:27 a.m.
Created at: April 17, 2026, 5:04 p.m.