Triple

T9929573
Position Surface form Disambiguated ID Type / Status
Subject Quercus wislizeni E192608 entity
Predicate authority P1330 FINISHED
Object A.DC. E231042 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: A.DC. | Statement: [Quercus wislizeni, authority, A.DC.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: A.DC.
Context triple: [Quercus wislizeni, authority, A.DC.]
  • A. DC. chosen
    DC. is the standard botanical author abbreviation for Augustin Pyramus de Candolle, a prominent Swiss botanist known for his influential work in plant taxonomy.
  • B. US-DC
    US-DC is the ISO 3166-2 code representing the District of Columbia, the federal district containing the capital city of the United States, Washington, D.C.
  • C. DC3
    DC3 is a public community college in Dodge City, Kansas, offering two-year academic and technical programs.
  • D. DCU
    DCU is a modern public university in Dublin, Ireland, known for its focus on innovation, research, and industry-oriented education.
  • E. DCU
    DCU is the common abbreviation for D.C. United, a professional Major League Soccer club based in Washington, D.C.
  • 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_69ca82dd978c8190947124ab0d3315ac completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb5b215c481909e0bca43f158bd82 completed April 2, 2026, 12:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69d20e258e888190ae4e2abac80e3399 completed April 5, 2026, 7:24 a.m.
Created at: March 30, 2026, 8:43 p.m.