Triple
T9936946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Girl, Interrupted |
E193982
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object | Lisa Rowe |
E261244
|
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: Lisa Rowe | Statement: [Girl, Interrupted, character, Lisa Rowe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lisa Rowe Context triple: [Girl, Interrupted, character, Lisa Rowe]
-
A.
Lisa Rowe
chosen
Lisa Rowe is a charismatic yet deeply troubled sociopath and fellow patient in the psychiatric drama film "Girl, Interrupted."
-
B.
Lisa Lynne
Lisa Lynne is an American Celtic harpist and composer known for her melodic, folk-inspired instrumental music and collaborations in the new age and world music genres.
-
C.
Crissy Haslam
Crissy Haslam is an American educator and former First Lady of Tennessee, known for her advocacy on literacy and children's issues during her husband Bill Haslam's governorship.
-
D.
Jayne Rowse
Jayne Rowse is a Michigan nurse and LGBT rights advocate known for challenging the state's same-sex marriage and adoption bans in the landmark DeBoer v. Snyder case.
-
E.
Lisa Douglas
Lisa Douglas is the glamorous, city-bred wife who struggles to adapt to rural farm life in the classic American sitcom "Green Acres."
- 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_69ca82e409348190a393777356b80a2a |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb5e4e19881909879b394090d6629 |
completed | April 2, 2026, 12:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d299d479d481908dc8fe2acc307a64 |
completed | April 5, 2026, 5:20 p.m. |
Created at: March 30, 2026, 8:44 p.m.