Triple
T20207281
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abéché |
E493385
|
entity |
| Predicate | roadConnection |
P385
|
FINISHED |
| Object | Adré |
—
|
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: Adré | Statement: [Abéché, roadConnection, Adré]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adré Context triple: [Abéché, roadConnection, Adré]
-
A.
Adré
chosen
Adré is a town in eastern Chad near the Sudanese border that serves as an important local commercial and administrative center in the Ouaddaï region.
-
B.
Eyraud
Eyraud is a French surname most notably borne by Eugène Eyraud, a 19th-century missionary known for his work on Easter Island.
-
C.
Leandre
Leandre is a French given name, cognate with Leander, traditionally associated with romantic and classical literary figures.
-
D.
Ondaine
The Ondaine is a river in central France that flows through the Loire department, notably passing by the town of Firminy.
-
E.
Moorenweis
Moorenweis is a rural municipality in Upper Bavaria, Germany, known for its agricultural landscape and small-village character.
- 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_69da6269614c8190bb40475d9d477358 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66d934f808190bbfeb96f5bf2dfb9 |
completed | April 20, 2026, 6:16 p.m. |
Created at: April 11, 2026, 11:38 p.m.