Triple

T20000992
Position Surface form Disambiguated ID Type / Status
Subject Quint E494324 entity
Predicate vehicle P7735 FINISHED
Object the Orca 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: the Orca | Statement: [Quint, vehicle, the Orca]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: the Orca
Context triple: [Quint, vehicle, the Orca]
  • A. Orca
    The orca, also known as the killer whale, is a highly intelligent, social, and powerful oceanic apex predator found in oceans worldwide.
  • B. Orca chosen
    Orca is a 1977 horror-thriller film about a vengeful killer whale that targets the fisherman who killed its mate.
  • C. Tokitae (orca)
    Tokitae (also known as Lolita) was a captive female orca who lived for decades at the Miami Seaquarium and became a prominent symbol in debates over marine mammal captivity and welfare.
  • D. Gisk’aast (Killer Whale)
    Gisk’aast (Killer Whale) is one of the principal matrilineal clans of the Nisga’a people, traditionally associated with the killer whale crest and its related histories, rights, and territories.
  • E. ORCA
    ORCA is a regional smart transit card system used for paying fares across multiple public transportation agencies in the Puget Sound region of Washington State.
  • 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e661a222908190b88e1d11cb1b7ee3 completed April 20, 2026, 5:25 p.m.
Created at: April 11, 2026, 3:32 p.m.