Triple
T1747159
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Olivia Langdon Clemens |
E38359
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Jean Clemens |
E17710
|
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: Jean Clemens | Statement: [Olivia Langdon Clemens, child, Jean Clemens]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jean Clemens Context triple: [Olivia Langdon Clemens, child, Jean Clemens]
-
A.
Jean Clemens
chosen
Jean Clemens was the youngest daughter of American author Mark Twain, remembered for her struggles with epilepsy and her close yet often tragic relationship with her father.
-
B.
Benjamin Garver Lamme
Benjamin Garver Lamme was an American electrical engineer and long-time Westinghouse chief engineer known for his pioneering work in alternating current machinery and power systems.
-
C.
George Hildebrand
George Hildebrand was an American Major League Baseball umpire active in the early 20th century.
-
D.
Louis Lingg
Louis Lingg was a German-born anarchist and labor activist best known as one of the defendants in the 1886 Haymarket affair in Chicago.
-
E.
Paul Luther
Paul Luther was a 16th-century German physician and the son of the Protestant Reformer Martin Luther.
- 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_69a8862b01a48190ab47209063af82d9 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69aa63eabdf48190878ecde3d1b1faf3 |
completed | March 6, 2026, 5:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ada0e058948190939e936af8f0e221 |
completed | March 8, 2026, 4:16 p.m. |
Created at: March 4, 2026, 7:31 p.m.