Triple
T9271713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zgorzelec |
E222843
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Avion |
E454082
|
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: Avion | Statement: [Zgorzelec, hasTwinTown, Avion]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Avion Context triple: [Zgorzelec, hasTwinTown, Avion]
-
A.
Avion
chosen
Avion is a commune in the Pas-de-Calais department in northern France.
-
B.
Aeroplan
Aeroplan is Air Canada's loyalty program that allows members to earn and redeem points for flights, upgrades, and other travel-related rewards.
-
C.
Aerograd
Aerograd is a 1935 Soviet science fiction and propaganda film directed by Alexander Dovzhenko, set in a futuristic Far Eastern border town threatened by foreign and internal enemies.
-
D.
Autavia
Autavia is a line of high-performance sports chronographs and watches by TAG Heuer, originally designed for automotive and aviation use.
-
E.
Altior
Altior is a celebrated British National Hunt racehorse renowned for his exceptional unbeaten streak over fences and multiple Grade 1 victories.
- 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_69ca841ffe208190aa7bcffbef2f8379 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd07865790819099b3865a25dae58a |
completed | April 1, 2026, 11:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d09c2ca500819083ef4aa37f3e3a7f |
completed | April 4, 2026, 5:05 a.m. |
Created at: March 30, 2026, 7:33 p.m.