Triple
T17687223
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrews |
E440925
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Thomas Andrews |
—
|
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: Thomas Andrews | Statement: [Andrews, hasNotableBearer, Thomas Andrews]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Andrews Context triple: [Andrews, hasNotableBearer, Thomas Andrews]
-
A.
Thomas Andrews
chosen
Thomas Andrews was a British shipbuilder and naval architect best known as the chief designer of the RMS Titanic, who perished during its sinking in 1912.
-
B.
Thomas Andrews Sr.
Thomas Andrews Sr. was a prominent 19th-century Irish industrialist and politician from County Down, known for his role in the linen industry and service as a Member of Parliament.
-
C.
George Dewar
George Dewar is a person associated with the use or application of the Dewar vessel, commonly linked to scientific or technical contexts.
-
D.
John Ballantyne
John Ballantyne is the amnesiac patient and central male protagonist in Alfred Hitchcock’s 1945 psychological thriller "Spellbound."
-
E.
John Wishart
John Wishart was a Scottish statistician known for the Wishart distribution, a fundamental probability distribution in multivariate statistics.
- 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_69d8b9e940b081908b862bb0e6e89b0d |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e470488c4081909b747313ef97b69c |
completed | April 19, 2026, 6:03 a.m. |
Created at: April 10, 2026, 10:03 a.m.