Triple
T28148977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ground Force |
E714559
|
entity |
| Predicate | featuredExpert |
P193877
|
FINISHED |
| Object | Alan Titchmarsh |
—
|
NE NERFINISHED |
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: Alan Titchmarsh | Statement: [Ground Force, featuredExpert, Alan Titchmarsh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuredExpert Context triple: [Ground Force, featuredExpert, Alan Titchmarsh]
-
A.
featuredDoctor
Indicates that a particular doctor is highlighted or promoted as a primary or notable medical professional in a given context.
-
B.
featuresPeople
chosen
Indicates that something prominently includes or showcases specific people as part of its content or presentation.
-
C.
featuresLeader
Indicates that one entity includes, presents, or highlights another entity in the role of a leader.
-
D.
featuredFor
Indicates that one entity is highlighted, promoted, or specially showcased in the context or for the benefit of another entity.
-
E.
featuredRegular
Indicates that an entity is designated as a regularly occurring or consistently highlighted feature within a given context.
- 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_69efd6b033208190bf74f80a147e2092 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69fe12a899d4819080d48423f32eace9 |
completed | May 8, 2026, 4:43 p.m. |
| PD | Predicate disambiguation | batch_69fe0d7f6aa08190a1d2dfc025d4e0dc |
completed | May 8, 2026, 4:21 p.m. |
Created at: April 27, 2026, 9:58 p.m.