Triple
T23581011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bobby Jones |
E582202
|
entity |
| Predicate | professionAfterGolf |
P153259
|
FINISHED |
| Object | lawyer in Atlanta |
—
|
LITERAL 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: lawyer in Atlanta | Statement: [Bobby Jones, professionAfterGolf, lawyer in Atlanta]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: professionAfterGolf Context triple: [Bobby Jones, professionAfterGolf, lawyer in Atlanta]
-
A.
roleInTigerWoodsCareer
Indicates the specific function, position, or contribution an entity has had within the context of Tiger Woods’s professional golf career.
-
B.
careerDoubles
Indicates the total number of doubles a person has achieved over the course of their entire career.
-
C.
careerSingles
Indicates the total number of singles (one-base hits) a player has accumulated over their entire career.
-
D.
designedGolfCourses
Indicates that one entity is the architect or creator responsible for designing the layout and features of one or more golf courses associated with another entity.
-
E.
professionBeforePolitics
Indicates that a person’s occupation or career occurred prior to their involvement in politics.
- F. None of above. chosen
Provenance (4 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_69e248f8d8248190acd5aee77f0d1709 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b02c265c819094728220d77172c6 |
completed | April 29, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69f118bcc0b08190b25a8dddfd461a0e |
completed | April 28, 2026, 8:29 p.m. |
| PDg | Predicate description generation | batch_69f12760784c8190aaeff002ef31febe |
completed | April 28, 2026, 9:32 p.m. |
Created at: April 17, 2026, 6:39 p.m.