Triple
T23210017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frankie Reed |
E580565
|
entity |
| Predicate | hasSibling |
P363
|
FINISHED |
| Object | Georgie Reed |
—
|
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: Georgie Reed | Statement: [Frankie Reed, hasSibling, Georgie Reed]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Georgie Reed Context triple: [Frankie Reed, hasSibling, Georgie Reed]
-
A.
Georgie Reed
chosen
Georgie Reed is a person known primarily as the sibling of Teddy Reed.
-
B.
Boyd Smith
Boyd Smith is an individual significant enough in his community or institution to have the Boyd and Jill Smith Family Stadium named in his honor.
-
C.
Chris Henry
Chris Henry is a renowned snooker coach and mental performance specialist who has worked with numerous top professional players.
-
D.
Aaron Ogden
Aaron Ogden was an early 19th-century American politician and steamboat operator whose state-granted monopoly became the focus of the landmark U.S. Supreme Court case Gibbons v. Ogden, which helped define federal power over interstate commerce.
-
E.
Ben Healy
Ben Healy is the mischievous, troublemaking young boy who serves as the central character in the "Problem Child" comedy film series.
- 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_69e24602ae1481908aaa6bc7ca493867 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f191609c64819096ace0d286d36f76 |
completed | April 29, 2026, 5:04 a.m. |
Created at: April 17, 2026, 4:07 p.m.