Triple
T2009596
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heather Mills |
E43660
|
entity |
| Predicate | hasPublicImage |
P13872
|
FINISHED |
| Object | controversial public figure |
—
|
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: controversial public figure | Statement: [Heather Mills, hasPublicImage, controversial public figure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPublicImage Context triple: [Heather Mills, hasPublicImage, controversial public figure]
-
A.
hasPhotograph
Indicates that one entity possesses, includes, or is associated with a photograph depicting or representing another entity.
-
B.
publicImage
chosen
Indicates how an entity is perceived or represented by the general public or broader audience.
-
C.
hasKeyImage
Indicates that one entity is designated as the primary or representative image associated with another entity.
-
D.
hasPortrait
Indicates that one entity possesses, displays, or is associated with a portrait depicting another entity.
-
E.
hasHiddenImage
Indicates that an entity contains or is associated with an image that is not immediately visible or is intentionally concealed from normal view.
- 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_69a88716e9f08190946313fdc949e3cf |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb89be08c81909eb5ea672ea46b2b |
completed | March 7, 2026, 5:33 a.m. |
| PD | Predicate disambiguation | batch_69abb7a03a1c81909ad50d56667db2d5 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:37 p.m.