Triple

T7703580
Position Surface form Disambiguated ID Type / Status
Subject Journal to Stella E174557 entity
Predicate featuresCharacter P626 FINISHED
Object Esther Johnson E685145 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: Esther Johnson | Statement: [Journal to Stella, featuresCharacter, Esther Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Esther Johnson
Context triple: [Journal to Stella, featuresCharacter, Esther Johnson]
  • A. Esther Johnson chosen
    Esther Johnson, affectionately known as "Stella," was the close companion and confidante of Jonathan Swift, to whom he addressed his famous "Journal to Stella" letters.
  • B. Esther Smith
    Esther Smith is the central teenage daughter in the classic 1944 MGM musical film "Meet Me in St. Louis," famously portrayed by Judy Garland.
  • C. Esther Dale
    Esther Dale was an American character actress known for her numerous supporting roles in Hollywood films and early television from the 1930s through the 1950s.
  • D. Esther Ross
    Esther Ross was the woman who served as the sponsor and ceremonial namesake figure for the U.S. Navy battleship USS Arizona (BB-39) at its christening.
  • E. Esther Harvey
    Esther Harvey was the wife of renowned American Broadway baritone and actor Alfred Drake.
  • 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_69c6995a72cc8190998e56daa6f8e453 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c7028bcb2c8190baa4e4b14abe2cc5 completed March 27, 2026, 10:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8be2583508190bda9a88e149fe264 completed March 29, 2026, 5:52 a.m.
Created at: March 27, 2026, 4:03 p.m.