Triple
T18893322
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Acun Ilıcalı |
E462146
|
entity |
| Predicate | founded |
P104
|
FINISHED |
| Object | Exxen |
—
|
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: Exxen | Statement: [Acun Ilıcalı, founded, Exxen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Exxen Context triple: [Acun Ilıcalı, founded, Exxen]
-
A.
Exxen
chosen
Exxen is a Turkish digital streaming platform offering original series, sports broadcasts, and entertainment content.
-
B.
Erixx
Erixx is a regional railway company in Germany that operates local passenger train services in Lower Saxony and surrounding areas.
-
C.
Ondexxya
Ondexxya is the brand name of andexanet alfa, a reversal agent used to counteract the anticoagulant effects of factor Xa inhibitors in cases of life-threatening or uncontrolled bleeding.
-
D.
Arlanxeo
Arlanxeo is a global synthetic rubber company specializing in high-performance elastomer products for the automotive, construction, and industrial sectors.
-
E.
Xanéu
Xanéu is an alternative name for the Terena language, an Arawakan language spoken by the Terena people of Brazil.
- 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_69d8dcfd05bc819088903cca13cc2846 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c47d392c81909297211c7d7610a1 |
completed | April 20, 2026, 6:15 a.m. |
Created at: April 10, 2026, 11:58 a.m.