Triple
T37955137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Faf de Klerk |
E946839
|
entity |
| Predicate | hasDistinctiveAppearance |
P143336
|
FINISHED |
| Object | long blond hair tied back during matches |
—
|
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: long blond hair tied back during matches | Statement: [Faf de Klerk, hasDistinctiveAppearance, long blond hair tied back during matches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDistinctiveAppearance Context triple: [Faf de Klerk, hasDistinctiveAppearance, long blond hair tied back during matches]
-
A.
hasDistinctiveShape
Indicates that an entity possesses a shape or form that is notably different from others and can be easily recognized or distinguished.
-
B.
hasTypicalAppearance
Indicates that an entity exhibits the standard or commonly expected visual form or look associated with its kind.
-
C.
describesAppearanceOf
chosen
Indicates that one entity provides information about the visual characteristics or outward look of another entity.
-
D.
hasDistinctiveEmblem
Indicates that an entity possesses a unique symbol, logo, or emblem that serves to distinguish it from others.
-
E.
appearanceIncludes
Indicates that one entity’s visual or outward characteristics contain, feature, or incorporate those of another entity.
- F. None of above.
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_69f76ef64cf08190ad3e1114b62aac67 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69ffada24d188190a576a02dc280a7fb |
completed | May 9, 2026, 9:56 p.m. |
| PD | Predicate disambiguation | batch_69ffad46d6ac819081772f408b1389d5 |
completed | May 9, 2026, 9:55 p.m. |
Created at: May 3, 2026, 4:20 p.m.