Triple
T2217894
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sean Penn |
E48073
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Michael Penn |
E135621
|
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: Michael Penn | Statement: [Sean Penn, sibling, Michael Penn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Penn Context triple: [Sean Penn, sibling, Michael Penn]
-
A.
Michael Penn
chosen
Michael Penn is an American singer-songwriter and composer known for his work on film scores and his 1989 hit single "No Myth."
-
B.
Jody Allen
Jody Allen is an American businesswoman and philanthropist, co-founder of Vulcan Inc. and sister of the late Microsoft co-founder Paul Allen.
-
C.
Mark Wills
Mark Wills is an American country music singer known for his late-1990s and early-2000s hits on the Billboard country charts.
-
D.
Dwight Fairfield
Dwight Fairfield is a nervous, teamwork-focused survivor character from the asymmetrical horror game Dead by Daylight.
-
E.
Sam O'Steen
Sam O'Steen was an acclaimed American film editor best known for his work on influential films such as "The Graduate," "Chinatown," and "Cool Hand Luke."
- 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_69a88aa1ee708190862c8c378c41e9eb |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc010bd4c8190ace293b37eac1de5 |
completed | March 7, 2026, 6:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae655b369c8190a5d12b87401534d7 |
completed | March 9, 2026, 6:14 a.m. |
Created at: March 4, 2026, 7:46 p.m.