Triple
T22071554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sam Donaldson |
E545419
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Donaldson |
—
|
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: Donaldson | Statement: [Sam Donaldson, familyName, Donaldson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donaldson Context triple: [Sam Donaldson, familyName, Donaldson]
-
A.
Donaldson
chosen
Donaldson is a surname of Scottish origin borne by various notable individuals, including athletes, politicians, and academics.
-
B.
Dodson
Dodson is a surname of English origin borne by various notable individuals across fields such as politics, sports, and the arts.
-
C.
Ted Donaldson
Ted Donaldson was an American child actor best known for his roles in 1940s films and radio, including the popular "A Date with Judy" series.
-
D.
Donaldson series
The Donaldson series is a generating function that encodes all Donaldson invariants of a smooth four-manifold into a single formal power series.
-
E.
Mark Donaldson
Mark Donaldson is an Australian soldier and war hero renowned for being the first person awarded the Victoria Cross for Australia for his gallantry in Afghanistan.
- 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_69e11e344dfc81909b1d88a7221329c7 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12888dcc08190b18d3d44d09ab943 |
completed | April 28, 2026, 9:37 p.m. |
Created at: April 16, 2026, 8:28 p.m.