Triple

T14724499
Position Surface form Disambiguated ID Type / Status
Subject Aaron Kendrick De Niro E345901 entity
Predicate paternalGrandmother P3524 FINISHED
Object Virginia Admiral E486960 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: Virginia Admiral | Statement: [Aaron Kendrick De Niro, paternalGrandmother, Virginia Admiral]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Virginia Admiral
Context triple: [Aaron Kendrick De Niro, paternalGrandmother, Virginia Admiral]
  • A. Virginia Admiral chosen
    Virginia Admiral was an American painter and poet associated with the mid-20th-century New York art scene and the mother of actor Robert De Niro.
  • B. Anson
    Anson is a commercial office building located in the Downtown Core of Singapore’s central business district.
  • C. Anson
    Anson is a masculine given name of English origin, historically borne by figures such as Anson Jones, the last president of the Republic of Texas.
  • D. Brig Williams
    Brig Williams was the British naval vessel commanded by Edward Bransfield during his early 19th-century exploratory voyages toward Antarctica.
  • E. Admiral Grant
    Admiral Grant is a fictional high-ranking naval officer portrayed by actor John Amos.
  • 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_69d822e5911c8190ba589f957dbd9ba7 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec25e9a14819081fa06fc601f295d completed April 14, 2026, 10:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdf09791e081908a1262717fd31445 completed May 8, 2026, 2:17 p.m.
Created at: April 10, 2026, 1:29 a.m.