Triple
T8045053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arras |
E187526
|
entity |
| Predicate | river |
P165
|
FINISHED |
| Object | Scarpe |
E82801
|
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: Scarpe | Statement: [Arras, river, Scarpe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scarpe Context triple: [Arras, river, Scarpe]
-
A.
Scarpe
chosen
The Scarpe is a river in northern France that flows through the Artois and Nord regions before joining the Scheldt.
-
B.
Sneakers
"Sneakers" is a 1992 comedic heist thriller film about a team of security experts who become entangled in espionage over a powerful code-breaking device.
-
C.
Car Shoe
Car Shoe is an Italian luxury footwear brand renowned for its handcrafted driving moccasins and casual shoes, operating under the Prada Group.
-
D.
Boots
Boots is a major British pharmacy-led health and beauty retailer and pharmacy chain with stores across the United Kingdom and other countries.
-
E.
Boots
"Boots" is Nancy Sinatra's 1966 debut studio album, best known for featuring her signature hit song "These Boots Are Made for Walkin'."
- 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_69ca82b00cb48190b59a300f70e97bd7 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3f4c79388190aecee6e313071a17 |
completed | March 31, 2026, 3:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc570cfad08190a8ed35ef2a47f497 |
completed | March 31, 2026, 11:21 p.m. |
Created at: March 30, 2026, 5:24 p.m.