Triple
T18160891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Rommely |
E434756
|
entity |
| Predicate | setting |
P1957
|
FINISHED |
| Object | Brooklyn |
—
|
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: Brooklyn | Statement: [Mary Rommely, setting, Brooklyn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brooklyn Context triple: [Mary Rommely, setting, Brooklyn]
-
A.
Brooklyn
chosen
Brooklyn is a populous and culturally diverse borough of New York City known for its distinct neighborhoods, arts scene, and iconic landmarks like the Brooklyn Bridge.
-
B.
Brooklyn
Brooklyn is a residential suburb within the Milnerton area of Cape Town, South Africa.
-
C.
Brooklyn
Brooklyn is a small city in Poweshiek County, Iowa, known for its collection of flags from around the world and its nickname "Community of Flags."
-
D.
Brooklyn
Brooklyn is a red-skinned, beaked gargoyle and the second-in-command of the Manhattan Clan in the animated television series "Gargoyles."
-
E.
Brooklyn
Brooklyn is a residential suburb within the coastal city of Burnie in Tasmania, Australia.
- 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_69d8b90b7a188190b3fc7b8d4a6cd20a |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4dec21e6081909070491f679c873c |
completed | April 19, 2026, 1:55 p.m. |
Created at: April 10, 2026, 10:30 a.m.