Triple
T13835374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eric Douglas |
E332511
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Joel Douglas |
E333965
|
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: Joel Douglas | Statement: [Eric Douglas, sibling, Joel Douglas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joel Douglas Context triple: [Eric Douglas, sibling, Joel Douglas]
-
A.
Joel Douglas
chosen
Joel Douglas is an American film producer known for his work on movies like "Romancing the Stone" and as the son of legendary actor Kirk Douglas.
-
B.
Joel Aldrich Matteson
Joel Aldrich Matteson was a 19th-century American politician who served as governor of Illinois.
-
C.
Joel Parker
Joel Parker is a name shared by several notable individuals, including historical American politicians and jurists.
-
D.
Joel Wilson
Joel Wilson is known as the brother of former child actress and writer Mara Wilson.
-
E.
Joel Fields
Joel Fields is an American television writer and producer best known for his work on acclaimed series such as The Americans and Fosse/Verdon.
- 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_69d81c5ae7c88190b0dd41bdafeb5999 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de029b352081909605baaedc336213 |
completed | April 14, 2026, 9:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c0ed7e8c81909ffed37f5b097188 |
completed | May 3, 2026, 9:41 p.m. |
Created at: April 9, 2026, 10:13 p.m.