Triple
T16231822
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bobbie Spencer |
E393999
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Tony Jones |
E1187953
|
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: Tony Jones | Statement: [Bobbie Spencer, spouse, Tony Jones]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tony Jones Context triple: [Bobbie Spencer, spouse, Tony Jones]
-
A.
Tony Jones
chosen
Tony Jones is a fictional physician from the soap opera "General Hospital," known for his complex personal relationships and dramatic storylines in Port Charles.
-
B.
Ron Jones
Ron Jones is an American composer best known for his work on television scores, including music for animated series such as "Family Guy" and "Star Trek: The Next Generation."
-
C.
Ron Jones
Ron Jones was a British television director best known for his work on the classic science fiction series Doctor Who during the 1980s.
-
D.
Dick Jones
Dick Jones is the corrupt senior executive and primary antagonist in the 1987 science fiction film "RoboCop."
-
E.
Kurt Jones
Kurt Jones is a cinematographer known for his work on the 2017 film "Beaches."
- 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_69d87f204df88190a8f88923decf9835 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e23d29fa248190943f4c3f7808908b |
completed | April 17, 2026, 2:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a001f8ae4288190b59e4af3e3d95000 |
completed | May 10, 2026, 6:02 a.m. |
Created at: April 10, 2026, 5:04 a.m.