Triple
T9030971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Darrell Rivers |
E216169
|
entity |
| Predicate | closeFriend |
P8712
|
FINISHED |
| Object | Alicia Johns |
E226959
|
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: Alicia Johns | Statement: [Darrell Rivers, closeFriend, Alicia Johns]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alicia Johns Context triple: [Darrell Rivers, closeFriend, Alicia Johns]
-
A.
Alicia Johns
chosen
Alicia Johns is a lively, mischievous, and sharp-tongued schoolgirl known for her pranks and strong personality in Enid Blyton’s Malory Towers series.
-
B.
Alicia Austin
Alicia Austin is an American illustrator and fantasy artist renowned for her distinctive work in science fiction and fantasy fandom, including award-winning fanzine and book illustrations.
-
C.
Alicia Bradford
Alicia Bradford was the wife of American industrialist and philanthropist Alfred I. du Pont.
-
D.
Alicia Clark
Alicia Clark is a central survivor and evolving leader in the television series "Fear the Walking Dead," known for her resilience, moral complexity, and growth amid the zombie apocalypse.
-
E.
Amaire Johnson
Amaire Johnson is a writer known for contributing to the work "Bounce Back."
- 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_69ca83a5fa88819088144801b4dd7245 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6a9f2c7481909b4a272183f20585 |
completed | April 1, 2026, 12:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d3549788608190a1949eb254e43a8e |
completed | April 6, 2026, 6:37 a.m. |
Created at: March 30, 2026, 7:08 p.m.