Triple
T17207952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Usakos |
E417649
|
entity |
| Predicate | connectedByRoadTo |
P11435
|
FINISHED |
| Object | Arandis |
E419949
|
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: Arandis | Statement: [Usakos, connectedByRoadTo, Arandis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arandis Context triple: [Usakos, connectedByRoadTo, Arandis]
-
A.
Arandis
chosen
Arandis is a small mining town in Namibia known primarily for its proximity to the Rossing uranium mine.
-
B.
Erandol
Erandol is a town in the Jalgaon district of Maharashtra, India, known for its agricultural economy and regional trading activities.
-
C.
Akhras
Akhras is a Syrian-origin family name best known for being the maiden surname of Asma al-Assad, the First Lady of Syria.
-
D.
Arnara
Arnara is a small municipality in the Lazio region of central Italy, located in the province of Frosinone.
-
E.
Arianda
Arianda is a surname best known through American actress Nina Arianda, acclaimed for her work on stage and screen.
- 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_69d886d779488190b131369541c04e7d |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42dc283648190b2c1f957940024aa |
completed | April 19, 2026, 1:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a015fe0a28c8190a76b3a356f7e0478 |
completed | May 11, 2026, 4:49 a.m. |
Created at: April 10, 2026, 5:38 a.m.