Triple
T9715908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | E.ON |
E235141
|
entity |
| Predicate | predecessor |
P97
|
FINISHED |
| Object | VEBA |
E815956
|
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: VEBA | Statement: [E.ON, predecessor, VEBA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: VEBA Context triple: [E.ON, predecessor, VEBA]
-
A.
VEBA
chosen
VEBA was a major German energy and industrial conglomerate that later became part of E.ON through a merger.
-
B.
VEBD
VEBD is the ICAO airport code for Bagdogra Airport, a major airport serving Siliguri and the surrounding region in West Bengal, India.
-
C.
VEBI
VEBI is the ICAO airport code for Shillong Airport, a domestic airport serving the city of Shillong in the Indian state of Meghalaya.
-
D.
VABO
VABO is the ICAO airport code assigned to Vadodara Airport in Gujarat, India.
-
E.
VEVRAA
VEVRAA is a U.S. federal law that requires certain federal contractors and subcontractors to take affirmative action to employ and advance qualified protected veterans.
- 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_69ca84cd8fa0819090a5e243ceb37003 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e0bb82081908e21a646f4de1a61 |
completed | April 1, 2026, 10:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1af9d6f148190b157cc7a0f91b387 |
completed | April 5, 2026, 12:41 a.m. |
Created at: March 30, 2026, 8:20 p.m.