Triple
T21517306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kléber (Paris Métro) |
E530877
|
entity |
| Predicate | hasNativeName |
P1435
|
FINISHED |
| Object | Kléber |
—
|
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: Kléber | Statement: [Kléber (Paris Métro), hasNativeName, Kléber]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kléber Context triple: [Kléber (Paris Métro), hasNativeName, Kléber]
-
A.
Kléber
chosen
Kléber is a French tire brand known for producing mid-range, reliable tires for passenger cars and light commercial vehicles.
-
B.
Emilio Kléber
Emilio Kléber was the nom de guerre of Manfred Stern, a Soviet military officer and Comintern agent best known for commanding International Brigades during the Spanish Civil War.
-
C.
Laurent Ney
Laurent Ney is a Belgian structural engineer and architect renowned for his innovative bridge designs and elegant, technically sophisticated public structures.
-
D.
Foucher
Foucher is a French surname most notably borne by Adèle Foucher, the wife of writer Victor Hugo.
-
E.
Jean-Baptiste Kléber
Jean-Baptiste Kléber was a prominent French general of the Revolutionary Wars, noted for his military skill in campaigns across Europe and the Middle East.
- 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_69e0c45d95a081908e7962ad215da746 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee814278e08190a66d516bed0726b5 |
completed | April 26, 2026, 9:18 p.m. |
Created at: April 16, 2026, 6:25 p.m.