Triple
T19461917
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walter Legge |
E486893
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Legge |
—
|
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: Legge | Statement: [Walter Legge, familyName, Legge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Legge Context triple: [Walter Legge, familyName, Legge]
-
A.
Legge
chosen
Legge is a surname most notably associated with Dorothy Haskell Porcher Legge, the Charleston preservationist credited with creating the iconic Rainbow Row of pastel-colored houses.
-
B.
Lawgi
Lawgi is a small rural locality within Queensland’s Banana Shire, known for its agricultural landscape and sparse population.
-
C.
Ley
Ley is an alternative spelling of the given name Leigh, used as a personal name or surname in English-speaking contexts.
-
D.
The Law
The Law is a prominent volcanic plug and hill in Dundee, Scotland, offering panoramic views over the city and the River Tay.
-
E.
The Law
The Law was a short-lived late-1980s rock supergroup formed by singer Paul Rodgers and drummer Kenney Jones, known for blending blues-rock and hard rock.
- 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633c983f481908b2684dc4380b889 |
completed | April 20, 2026, 2:10 p.m. |
Created at: April 10, 2026, 1:38 p.m.