Triple
T11050903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lisa Rowe |
E261244
|
entity |
| Predicate | hasRelationshipWith |
P2830
|
FINISHED |
| Object | Susanna Kaysen |
E831340
|
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: Susanna Kaysen | Statement: [Lisa Rowe, hasRelationshipWith, Susanna Kaysen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Susanna Kaysen Context triple: [Lisa Rowe, hasRelationshipWith, Susanna Kaysen]
-
A.
Susanna Kaysen
chosen
Susanna Kaysen is an American writer best known for her memoir "Girl, Interrupted," which recounts her experiences in a psychiatric hospital in the 1960s.
-
B.
Meredith Logue
Meredith Logue is a fictional wealthy socialite character portrayed by Cate Blanchett in the 1999 film "The Talented Mr. Ripley."
-
C.
Rosalyn Tureck
Rosalyn Tureck was an American pianist and harpsichordist renowned for her pioneering, intellectually rigorous interpretations of Johann Sebastian Bach’s keyboard works.
-
D.
Lili Jellinek
Lili Jellinek was a member of the Jellinek family associated with the early history of the Mercedes automobile brand.
-
E.
Sybil Newman
Sybil Newman is known as the former spouse of American screenwriter and producer William Broyles Jr.
- 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_69d6aa98650481908609c7c56bfa7902 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d798698bd88190aa97afd37f55e19f |
completed | April 9, 2026, 12:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3aa146b148190a87205e542cc718f |
completed | April 18, 2026, 3:58 p.m. |
Created at: April 8, 2026, 9:26 p.m.