Triple
T13254334
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katharine Smith |
E315618
|
entity |
| Predicate | siblingOf |
P363
|
FINISHED |
| Object | William Smith |
E218257
|
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: William Smith | Statement: [Katharine Smith, siblingOf, William Smith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William Smith Context triple: [Katharine Smith, siblingOf, William Smith]
-
A.
William Smith
chosen
William Smith was a 19th-century American religious leader best known as a younger brother of Joseph Smith and an early apostle in the Latter Day Saint movement.
-
B.
William Smith
William Smith was a British sealer and explorer credited with the early 19th-century discovery of the South Shetland Islands in the Southern Ocean.
-
C.
William Smith
William Smith was the second husband of famed Broadway and film musical star Ethel Merman.
-
D.
William Smith
William Smith was the birth name of American character actor Franklyn Farnum, who appeared in numerous films and early television productions.
-
E.
William Smith
William Smith was an American character actor and bodybuilder best known for his tough-guy roles in film and television from the 1960s through the 1980s.
- 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_69d806b1072881909e46bd212259c5f0 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98f7517048190b4eac4e44e81ff66 |
completed | April 11, 2026, 12:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f70a3d6b808190b4ae5225961de03f |
completed | May 3, 2026, 8:41 a.m. |
Created at: April 9, 2026, 9:24 p.m.