Triple
T21038263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irving Mills |
E518249
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Jack Mills |
—
|
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: Jack Mills | Statement: [Irving Mills, sibling, Jack Mills]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jack Mills Context triple: [Irving Mills, sibling, Jack Mills]
-
A.
Jack Mills
chosen
Jack Mills was a British librarian and information scientist known for his influential work in classification theory and library cataloguing systems.
-
B.
Victor Melling
Victor Melling is a refined, exacting beauty pageant coach and mentor featured in the comedy film "Miss Congeniality."
-
C.
Lewis Milles
Lewis Milles was an English politician who served as a Member of Parliament in the early 18th century.
-
D.
Frank Mills
Frank Mills is a Canadian pianist and composer best known for his easy-listening instrumental hit "Music Box Dancer."
-
E.
Onslow Stevens
Onslow Stevens was an American character actor active from the 1930s to the 1950s, known for his supporting roles in numerous Hollywood films and early television productions.
- 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_69e0b50438e08190917e2538bb8bc034 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fcee13b08190a8b3372f6759cd1b |
completed | April 21, 2026, 4:28 a.m. |
Created at: April 16, 2026, 2:12 p.m.