Triple
T12780519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emanuel Lasker |
E305494
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Lasker |
E305494
|
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: Lasker | Statement: [Emanuel Lasker, familyName, Lasker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lasker Context triple: [Emanuel Lasker, familyName, Lasker]
-
A.
Lasker
chosen
Lasker is a surname most famously associated with figures such as Emanuel Lasker, the long-reigning World Chess Champion, and Albert Lasker, a pioneering American advertising executive.
-
B.
Emanuel Lasker
Emanuel Lasker was a German mathematician and the second World Chess Champion, renowned for holding the title for a record 27 years from 1894 to 1921.
-
C.
Aleksandr Levitsky
Aleksandr Levitsky was a Soviet cinematographer known for his work on early silent films, including collaborations with pioneering directors of the 1920s.
-
D.
Edward Lasker
Edward Lasker was an American film producer and studio executive active in Hollywood during the mid-20th century.
-
E.
Reuben Lasker
Reuben Lasker was a prominent American fisheries biologist known for his influential research on fish larvae and marine ecosystems.
- 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_69d7bdf2b43c819098ae5aa68e61ea58 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e5a5680819095dcd491486d23e7 |
completed | April 10, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f685030cbc8190856bf5254e231d25 |
completed | May 2, 2026, 11:13 p.m. |
Created at: April 9, 2026, 5:29 p.m.