Triple
T25617971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sugar Ray Robinson |
E642208
|
entity |
| Predicate | colorLineEra |
P159471
|
FINISHED |
| Object | post-Joe Louis era of American boxing |
—
|
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: post-Joe Louis era of American boxing | Statement: [Sugar Ray Robinson, colorLineEra, post-Joe Louis era of American boxing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: colorLineEra Context triple: [Sugar Ray Robinson, colorLineEra, post-Joe Louis era of American boxing]
-
A.
colorLineContext
Indicates a relationship where the color of a line is determined or interpreted based on its surrounding contextual information or environment.
-
B.
formerLineColor
Indicates that an entity previously had a specific line color before it was changed to a different one.
-
C.
colorVersionReleaseYear
Indicates the year in which a particular color version of something was released.
-
D.
servedByLineColor
Indicates that a transit service or route is operated using vehicles or infrastructure associated with a specific line color.
-
E.
arcColor
Indicates the color attribute assigned to an arc in a graph or network representation.
- 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_69e77e7a96748190b10f2699041e4e43 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5f9e8734c8190a214685b1647abe1 |
completed | May 2, 2026, 1:19 p.m. |
| PD | Predicate disambiguation | batch_69f4a0f7c6008190ae8cee3e71e19b94 |
completed | May 1, 2026, 12:47 p.m. |
| PDg | Predicate description generation | batch_69f55e497fa081909bc59a7b92c5df59 |
completed | May 2, 2026, 2:15 a.m. |
Created at: April 21, 2026, 5:01 p.m.