Triple
T7452525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | European Anti-Fraud Office |
E172040
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object |
OLAF
OLAF is the European Union’s anti-fraud office responsible for investigating fraud, corruption, and other illegal activities affecting the EU’s financial interests.
|
E665687
|
NE FINISHED |
How this triple was built (4 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: OLAF | Statement: [European Anti-Fraud Office, shortName, OLAF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: OLAF Context triple: [European Anti-Fraud Office, shortName, OLAF]
-
A.
Holger
Holger is a masculine given name of Scandinavian origin, commonly used in countries such as Sweden and Denmark.
-
B.
Inspector Krogh
Inspector Krogh is a wooden-armed police inspector in the 1939 horror film "Son of Frankenstein," known for his stern demeanor and memorable portrayal by actor Lionel Atwill.
-
C.
Investigator Strait
Investigator Strait is a body of water off the coast of South Australia that separates Yorke Peninsula from Kangaroo Island.
-
D.
Rothbart
Rothbart is the dark sorcerer and primary antagonist in the ballet "Swan Lake," responsible for cursing Odette and driving the central conflict of the story.
-
E.
Bork
Bork is the surname of Robert Bork, a prominent American jurist and former U.S. Supreme Court nominee.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: OLAF Triple: [European Anti-Fraud Office, shortName, OLAF]
Generated description
OLAF is the European Union’s anti-fraud office responsible for investigating fraud, corruption, and other illegal activities affecting the EU’s financial interests.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: OLAF Target entity description: OLAF is the European Union’s anti-fraud office responsible for investigating fraud, corruption, and other illegal activities affecting the EU’s financial interests.
-
A.
Holger
Holger is a masculine given name of Scandinavian origin, commonly used in countries such as Sweden and Denmark.
-
B.
Inspector Krogh
Inspector Krogh is a wooden-armed police inspector in the 1939 horror film "Son of Frankenstein," known for his stern demeanor and memorable portrayal by actor Lionel Atwill.
-
C.
Investigator Strait
Investigator Strait is a body of water off the coast of South Australia that separates Yorke Peninsula from Kangaroo Island.
-
D.
Rothbart
Rothbart is the dark sorcerer and primary antagonist in the ballet "Swan Lake," responsible for cursing Odette and driving the central conflict of the story.
-
E.
Bork
Bork is the surname of Robert Bork, a prominent American jurist and former U.S. Supreme Court nominee.
- F. None of above. chosen
Provenance (5 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_69c68a66554c8190add75c65942c0317 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f38d6a8c8190af2e73c719da87a6 |
completed | March 27, 2026, 9:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c827b9a6048190bd3e3594b9cff2b7 |
completed | March 28, 2026, 7:10 p.m. |
| NEDg | Description generation | batch_69c828e1487081908de825d60ea38c9e |
completed | March 28, 2026, 7:15 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c829d8a15c8190911e0d7bda39c280 |
completed | March 28, 2026, 7:19 p.m. |
Created at: March 27, 2026, 3:14 p.m.