Triple

T13979288
Position Surface form Disambiguated ID Type / Status
Subject SBU E336265 entity
Predicate fullName P16 FINISHED
Object Special Boarding Unit E66999 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: Special Boarding Unit | Statement: [SBU, fullName, Special Boarding Unit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Special Boarding Unit
Context triple: [SBU, fullName, Special Boarding Unit]
  • A. Special Boarding Unit chosen
    The Special Boarding Unit is an elite Japanese maritime special operations force specializing in counter-terrorism, anti-piracy, and ship-boarding missions.
  • B. Special Paratrooper Unit
    The Special Paratrooper Unit is an elite airborne commando formation of the Hellenic Army Special Forces, trained for high-risk rapid deployment and special operations.
  • C. Special Actions Unit
    The Special Actions Unit is an elite counter-terrorism and special operations tactical team of the Royal Malaysia Police.
  • D. Special Duty Group
    The Special Duty Group is an elite commando unit of India’s Central Reserve Police Force specializing in high-risk counterinsurgency and counterterrorism operations.
  • E. Special Unit 2
    Special Unit 2 is an American television series that blends comedy and science fiction as it follows a secret police unit tasked with hunting down mythological creatures living undercover in modern-day Chicago.
  • 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_69d81c639e808190a0e4b4f3d31c6a59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2e9fc7248190a9f26e253286ac3c completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fba1e3cafc8190a1806a29b2e46ae9 completed May 6, 2026, 8:17 p.m.
Created at: April 9, 2026, 10:18 p.m.