Triple
T11869336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ellen O'Hara |
E282365
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Katie Scarlett O'Hara |
E255144
|
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: Katie Scarlett O'Hara | Statement: [Ellen O'Hara, child, Katie Scarlett O'Hara]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Katie Scarlett O'Hara Context triple: [Ellen O'Hara, child, Katie Scarlett O'Hara]
-
A.
Katie Scarlett O'Hara
chosen
Katie Scarlett O'Hara is the headstrong, resourceful Southern heroine of Margaret Mitchell's novel "Gone with the Wind" and its film adaptation.
-
B.
Scarlett Curtis
Scarlett Curtis is a British writer, activist, and feminist known for her work on mental health advocacy and for editing the bestselling anthology "Feminists Don't Wear Pink (and Other Lies)."
-
C.
Tulip O’Hare
Tulip O’Hare is a fiercely resourceful and violent yet charismatic outlaw and the ex-girlfriend of Jesse Custer in the comic book and television series "Preacher."
-
D.
Kathryn
Kathryn is a feminine given name, commonly considered a variant spelling of Katherine/Catherine.
-
E.
Janet McQueen
Janet McQueen is a sibling of the renowned British fashion designer Alexander McQueen.
- 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a73c04e4819084c0b2ff8e5d2f04 |
completed | April 10, 2026, 7:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f281a2abfc8190a4769e637dedaaab |
completed | April 29, 2026, 10:09 p.m. |
Created at: April 8, 2026, 9:43 p.m.