Triple
T16483349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kölner Haie |
E400376
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | Die Haie |
E400376
|
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: Die Haie | Statement: [Kölner Haie, nickname, Die Haie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Die Haie Context triple: [Kölner Haie, nickname, Die Haie]
-
A.
Die Haie
chosen
Die Haie is the popular nickname of the Kölner Haie, a professional ice hockey team based in Cologne, Germany.
-
B.
El Gran Pez
El Gran Pez is the popular nickname of the Mexican football club Dorados de Sinaloa, reflecting its identity and local cultural ties.
-
C.
La Raie
La Raie is the French title of the 1982 American horror anthology film "Creepshow."
-
D.
The Great Shark Hunt
The Great Shark Hunt is a collection of Hunter S. Thompson’s gonzo journalism and essays spanning his career, showcasing his signature wild, satirical, and politically charged style.
-
E.
Haus des Meeres
Haus des Meeres is a public aquarium and zoo in Vienna, Austria, housed in a former World War II flak tower and known for its diverse marine and tropical animal exhibits.
- 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_69d883813098819084f5409539723b59 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e0420ac81908f9a3548ddb3b1ff |
completed | April 18, 2026, 7:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00607aafa48190929250a879c602ca |
completed | May 10, 2026, 10:39 a.m. |
Created at: April 10, 2026, 5:13 a.m.