Triple
T6323679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jonathan Apphus |
E141806
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | John Gaddi |
E507615
|
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: John Gaddi | Statement: [Jonathan Apphus, sibling, John Gaddi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Gaddi Context triple: [Jonathan Apphus, sibling, John Gaddi]
-
A.
John Gaddi
chosen
John Gaddi was a member of the prominent Hasmonean family in the 2nd century BCE, known primarily as a brother of the Jewish leader Simon Thassi.
-
B.
Vincent Gaddis
Vincent Gaddis was an American writer and researcher best known for coining and popularizing the modern mystery surrounding the Bermuda Triangle in the mid-20th century.
-
C.
Greg Finton
Greg Finton is a film editor known for his work on documentaries and feature films, including the acclaimed documentary "He Named Me Malala."
-
D.
Mike Gaffey
Mike Gaffey is a songwriter best known for co-writing the track "RITMO (Bad Boys for Life)."
-
E.
Michael Sarnoski
Michael Sarnoski is an American filmmaker and screenwriter best known for directing the acclaimed drama "Pig" and later helming the horror prequel "A Quiet Place: Day One."
- 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_69c008d201748190917e69c41ba3f978 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c064e538ac81908c5d7556513c2bc3 |
completed | March 22, 2026, 9:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7daf2ac9c81909a029c784cc70827 |
completed | March 28, 2026, 1:43 p.m. |
Created at: March 22, 2026, 4:29 p.m.