Triple
T16301428
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Anne Frere |
E395797
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Frere |
E383602
|
NE 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: Frere | Statement: [Mary Anne Frere, familyName, Frere]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frere Context triple: [Mary Anne Frere, familyName, Frere]
-
A.
Frere
chosen
Frere is an English surname most notably associated with Sir Henry Bartle Frere, a 19th-century British colonial administrator and diplomat.
-
B.
Lafresnaye
Lafresnaye was a 19th-century French ornithologist known for describing numerous bird species.
-
C.
Frantz
Frantz is the given name of Frantz Fanon, the influential Martinican psychiatrist, philosopher, and anti-colonial theorist.
-
D.
Freidig
Freidig is the former name of the Norwegian football club Hamarkameratene, commonly known as HamKam.
-
E.
La Frenais
La Frenais is a surname most notably associated with British television writer Ian La Frenais, known for co-creating several classic UK comedy series.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e25e32da7081908d8bd320374a5731 |
completed | April 17, 2026, 4:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a001f9fb2908190a8521b1ccf49170a |
completed | May 10, 2026, 6:03 a.m. |
Created at: April 10, 2026, 5:06 a.m.