Triple
T12295691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joe Freeman |
E293078
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Grace Freeman |
E288555
|
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: Grace Freeman | Statement: [Joe Freeman, sibling, Grace Freeman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Grace Freeman Context triple: [Joe Freeman, sibling, Grace Freeman]
-
A.
Grace Freeman
chosen
Grace Freeman is the daughter of English actor Martin Freeman.
-
B.
Chelsea Freeman
Chelsea Freeman is an American entrepreneur and social media personality best known as the wife of Major League Baseball star Freddie Freeman.
-
C.
Katherine Noelle Wyman
Katherine Noelle Wyman is the daughter of Bill Wyman, the former bassist of the Rolling Stones.
-
D.
Jessica Williams
Jessica Williams is an American actress and comedian best known as a former correspondent on The Daily Show and for her roles in films and television series such as The Incredible Jessica James and Love Life.
-
E.
Jennifer Williams
Jennifer Williams is known as the daughter of acclaimed American composer and conductor John Williams.
- 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_69d6ab690ad081908c0ed3870ec82d53 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93ed903808190b7ed90e0db3d7586 |
completed | April 10, 2026, 6:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f61e79bf548190bf7f314222ed1ed1 |
completed | May 2, 2026, 3:55 p.m. |
Created at: April 8, 2026, 9:52 p.m.