Triple
T28344789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Atkinson |
E717918
|
entity |
| Predicate | isAmbiguousIn |
P164421
|
FINISHED |
| Object | sports context |
—
|
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: sports context | Statement: [George Atkinson, isAmbiguousIn, sports context]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isAmbiguousIn Context triple: [George Atkinson, isAmbiguousIn, sports context]
-
A.
hasAmbiguous
Indicates that the relationship or state is unclear, uncertain, or open to multiple interpretations.
-
B.
isAmbiguousName
Indicates that a name can refer to multiple distinct entities or interpretations, making its reference unclear without additional context.
-
C.
isAmbiguousWithinUSStates
Indicates that the referenced item has multiple possible interpretations or matches when considered across U.S. states, and thus cannot be uniquely associated with a single state context.
-
D.
hasAmbiguousIdentity
Indicates that an entity’s identity is unclear, uncertain, or can be interpreted in multiple distinct ways.
-
E.
hasAmbiguousEnding
Indicates that the event, story, or situation concludes in a way that is open to multiple interpretations or lacks a clear, definitive resolution.
- 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_69eff6eb30388190b898b96c4be6f49d |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64c5645d48190b0c3a2bad5a2e539 |
completed | May 2, 2026, 7:11 p.m. |
| PD | Predicate disambiguation | batch_69f641e2f1708190b45b48d6a43c51d2 |
completed | May 2, 2026, 6:26 p.m. |
| PDg | Predicate description generation | batch_69f64bca8574819095e081cbb7e2f369 |
completed | May 2, 2026, 7:08 p.m. |
Created at: April 28, 2026, 12:42 a.m.