Triple
T22116730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Broom |
E546563
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Broom |
—
|
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: Broom | Statement: [Robert Broom, familyName, Broom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Broom Context triple: [Robert Broom, familyName, Broom]
-
A.
broom
chosen
A broom is a simple cleaning tool with a long handle and bristles used for sweeping floors and other surfaces.
-
B.
Stonebroom
Stonebroom is a village in Derbyshire, England, known as a small former mining community in the East Midlands.
-
C.
High Brooms
High Brooms is a suburban area of Royal Tunbridge Wells in Kent, England, known primarily as a residential district served by its local railway station.
-
D.
Skreemer
Skreemer is a dystopian science fiction comic series known for its complex, literary storytelling and crime-laden future setting.
-
E.
Bludger
A Bludger is a bewitched, heavy iron ball in the Harry Potter universe’s sport of Quidditch that violently zooms around the pitch trying to knock players off their brooms.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e38b3848190ac3a4fa97d56e65a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1294e85708190b455846bacbdfd03 |
completed | April 28, 2026, 9:40 p.m. |
Created at: April 16, 2026, 8:31 p.m.