Triple
T22607947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary McDonnell |
E566612
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | Michael Mell |
—
|
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: Michael Mell | Statement: [Mary McDonnell, hasChild, Michael Mell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Mell Context triple: [Mary McDonnell, hasChild, Michael Mell]
-
A.
Michael Mell
chosen
Michael Mell is known as the son of American actress Mary McDonnell.
-
B.
Michael Christ
Michael Christ is a mathematician known for his contributions to harmonic analysis and partial differential equations, and for being a student of Elias Stein.
-
C.
Michael Matheson
Michael Matheson is a Scottish National Party politician who has served as a Member of the Scottish Parliament and held several senior ministerial roles in the Scottish Government.
-
D.
Michaelangelo Moran
Michaelangelo Moran is an Indonesian entrepreneur and designer best known as a co-founder of the ride-hailing and super-app company Gojek.
-
E.
Michael Athans
Michael Athans was a prominent control theorist and MIT professor known for his pioneering contributions to modern control theory and systems engineering.
- 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_69e245884860819081046ce07d5872c4 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f167e75658819089153eab7563540c |
completed | April 29, 2026, 2:07 a.m. |
Created at: April 17, 2026, 2:55 p.m.