Triple

T9656300
Position Surface form Disambiguated ID Type / Status
Subject SCUT E233459 entity
Predicate affiliation P10 FINISHED
Object Project 985 E35126 NE FINISHED

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: Project 985 | Statement: [SCUT, affiliation, Project 985]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Project 985
Context triple: [SCUT, affiliation, Project 985]
  • A. Project 985 chosen
    Project 985 is a Chinese government initiative launched in 1998 to develop a group of elite universities into world-class institutions through targeted funding and support.
  • B. Project 211
    Project 211 is a Chinese government initiative launched to strengthen about 100 key universities and colleges in the 21st century by prioritizing them for additional funding and development.
  • C. Project 523
    Project 523 was a secret Chinese government research initiative launched during the Vietnam War to develop new antimalarial treatments, ultimately leading to the discovery of artemisinin.
  • D. Project 1950
    Project 1950 is a Misfits studio album featuring punk rock covers of classic 1950s and 1960s pop songs.
  • E. Project 949
    Project 949 is the Soviet/Russian design designation for the Oscar-class nuclear-powered cruise missile submarines built for long-range anti-ship warfare.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca848c1ba88190b84b410cd14627fc completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9bdd5c0c8190a6c82a1609454d1b completed April 1, 2026, 10:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69d18a07444c819099d7462c38f6da49 completed April 4, 2026, 10 p.m.
Created at: March 30, 2026, 8:14 p.m.