Triple

T6523627
Position Surface form Disambiguated ID Type / Status
Subject Trans–New Guinea languages E151246 entity
Predicate laterWorkBy P71402 FINISHED
Object Malcolm Ross E211265 NE FINISHED

How this triple was built (3 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: Malcolm Ross | Statement: [Trans–New Guinea languages, laterWorkBy, Malcolm Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Malcolm Ross
Context triple: [Trans–New Guinea languages, laterWorkBy, Malcolm Ross]
  • A. Malcolm Ross chosen
    Malcolm Ross is a linguist known for his influential work on the classification and historical relationships of Papuan and Oceanic languages, particularly in the Northwest Solomonic region.
  • B. Malcolm Dixon
    Malcolm Dixon was a British actor and dwarf performer best known for his roles in fantasy and science-fiction films of the late 20th century.
  • C. Malcolm Kirk
    Malcolm Kirk was an English professional wrestler known for his imposing size and for tragically dying in the ring during a match in 1987.
  • D. Malcolm Elliott
    Malcolm Elliott was a notable figure in Alaska’s history, commemorated by having the Elliott Highway named in his honor.
  • E. Malcolm Waite
    Malcolm Waite was an American silent film actor best remembered for his supporting roles in early Hollywood comedies, including Charlie Chaplin films.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: laterWorkBy
Context triple: [Trans–New Guinea languages, laterWorkBy, Malcolm Ross]
  • A. laterWork
    Indicates that one work was created, published, or produced after another work in time.
  • B. laterIn
    Indicates that one event, state, or time point occurs after another in temporal order.
  • C. laterActivity
    Indicates that one activity occurs after another in time, establishing a temporal ordering between them.
  • D. lastWork
    Indicates that one entity is the most recent work (e.g., creation, project, or publication) associated with another entity.
  • E. hasWorkBy
    Indicates that one entity (such as a collection, exhibition, or publication) includes or contains creative works produced by another entity (such as an artist, author, or creator).
  • F. None of above. chosen

Provenance (5 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_69c687f522748190b3058405553cdabd completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6ad970afc81909d3231203eacf413 completed March 27, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6cb74dfac81908eb44811869450ae completed March 27, 2026, 6:24 p.m.
PD Predicate disambiguation batch_69c68abbc7148190a8270d47fe10cc31 completed March 27, 2026, 1:48 p.m.
PDg Predicate description generation batch_69c69f362ee4819090e8fa48caef7d7d completed March 27, 2026, 3:16 p.m.
Created at: March 27, 2026, 1:45 p.m.