Triple
T22840538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pieces of Her |
E566066
|
entity |
| Predicate | protagonist |
P268
|
FINISHED |
| Object | Laura Oliver |
—
|
NE NERFINISHED |
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: Laura Oliver | Statement: [Pieces of Her, protagonist, Laura Oliver]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laura Oliver Context triple: [Pieces of Her, protagonist, Laura Oliver]
-
A.
Laura Oliver
chosen
Laura Oliver is the enigmatic mother at the center of Karin Slaughter’s thriller "Pieces of Her," whose violent past and hidden identity upend her daughter’s understanding of their lives.
-
B.
Rachel Lapp
Rachel Lapp is a young Amish widow and mother who becomes entangled with a big-city detective in the 1985 crime thriller film "Witness."
-
C.
Laura Hawkins
Laura Hawkins was a childhood friend and early love interest of Mark Twain whose personality and experiences inspired the character Becky Thatcher in "The Adventures of Tom Sawyer."
-
D.
Emily Greer
Emily Greer is a notable individual recognized as a prominent bearer of the surname Greer.
-
E.
Sarah Condon
Sarah Condon is a television producer best known for her work as an executive producer on acclaimed HBO series such as "Looking" and "Bored to Death."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245869e188190a196584f36e682da |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17e83fa48819084568264ef45c833 |
completed | April 29, 2026, 3:44 a.m. |
Created at: April 17, 2026, 3:35 p.m.