Triple
T2151442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York World |
E47188
|
entity |
| Predicate | employed |
P7
|
FINISHED |
| Object | Nellie Bly |
E35843
|
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: Nellie Bly | Statement: [New York World, employed, Nellie Bly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nellie Bly Context triple: [New York World, employed, Nellie Bly]
-
A.
Nellie Bly
chosen
Nellie Bly was a pioneering American journalist and investigative reporter famed for her undercover exposés and record-setting trip around the world in 72 days.
-
B.
Ellen Gleason
Ellen Gleason is a member of the Gleason family, related to pioneering American engineer and businesswoman Kate Gleason.
-
C.
Blanche Sewell
Blanche Sewell was an American film editor best known for her work on classic Hollywood productions, including the 1939 musical fantasy film "The Wizard of Oz."
-
D.
Briton Hadden
Briton Hadden was an American journalist and co-founder of Time magazine, instrumental in shaping modern news reporting and magazine journalism.
-
E.
Sue Snell
Sue Snell is a remorseful high school student in Stephen King’s novel "Carrie," whose attempt to atone for bullying the title character inadvertently contributes to the story’s tragic climax.
- 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_69a88a1933e0819094f18426ed74180f |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbe4747a0819080e2234f3ea8995f |
completed | March 7, 2026, 5:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae5d940bec8190998ef88ed44e5811 |
completed | March 9, 2026, 5:41 a.m. |
Created at: March 4, 2026, 7:44 p.m.