Triple
T11138566
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joe McGann |
E263478
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Mark McGann |
E267359
|
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: Mark McGann | Statement: [Joe McGann, sibling, Mark McGann]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark McGann Context triple: [Joe McGann, sibling, Mark McGann]
-
A.
Mark McGann
chosen
Mark McGann is an English actor and director known for his work in television, film, and theatre, and as one of the four acting McGann brothers.
-
B.
Tom McDonough
Tom McDonough is an editor and writer known for his work on the publication "A Gunfight."
-
C.
John McMullen
John McMullen was a 19th-century Catholic bishop and civic leader known for his role in establishing educational and religious institutions in the American Midwest.
-
D.
Scott McAuliffe
Scott McAuliffe is the son of Christa McAuliffe, the teacher and astronaut who died in the 1986 Space Shuttle Challenger disaster.
-
E.
Patrick Eagan
Patrick Eagan was an early Irish immigrant settler and local political figure after whom the city of Eagan, Minnesota, is named.
- 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_69d6aa9c0ba08190bbd19c217489b755 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e85f2ea48190bf1ff63af1d7d236 |
completed | April 9, 2026, 5:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5562a0f54819095360368672d2e96 |
completed | April 19, 2026, 10:24 p.m. |
Created at: April 8, 2026, 9:28 p.m.