Triple
T17800012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martha Byrne |
E444396
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Byrne |
—
|
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: Byrne | Statement: [Martha Byrne, familyName, Byrne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Byrne Context triple: [Martha Byrne, familyName, Byrne]
-
A.
Byrne
chosen
Byrne is a common Irish surname borne by numerous notable figures in fields such as literature, entertainment, and politics.
-
B.
Byrnes
Byrnes is a surname of Irish origin borne by various notable individuals, including American politician and statesman James F. Byrnes.
-
C.
O'Byrne
O'Byrne is an Irish surname, a variant of Byrne, traditionally associated with Gaelic families from County Wicklow and surrounding regions.
-
D.
Byrns
Byrns is a surname most notably associated with Joseph W. Byrns, a prominent early 20th-century American politician and Speaker of the U.S. House of Representatives.
-
E.
Browne
Browne is the surname of Lord Browne of Madingley, the prominent British businessman and former chief executive of BP.
- 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_69d8b9efe370819095cd219b143ae727 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e487fe19dc8190b7e9dc96f39e0861 |
completed | April 19, 2026, 7:45 a.m. |
Created at: April 10, 2026, 10:13 a.m.