Triple

T16121971
Position Surface form Disambiguated ID Type / Status
Subject Citroën AX E391168 entity
Predicate trimLevel P11486 FINISHED
Object AX 11
AX 11 is a specific trim level of the Citroën AX supermini, typically featuring a modestly more powerful engine and upgraded equipment over the base models.
 E1196648 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: AX 11 | Statement: [Citroën AX, trimLevel, AX 11]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AX 11
Context triple: [Citroën AX, trimLevel, AX 11]
  • A. AXK
    AXK is the ICAO airline designator assigned to African Express Airways, a regional carrier based in Kenya.
  • B. AXT
    AXT is the three-letter IATA airport code for Akita Airport in Akita Prefecture, Japan.
  • C. AXJ
    AXJ is the IATA airport code for Amakusa Airfield, a regional airport serving the Amakusa Islands in Kumamoto Prefecture, Japan.
  • D. X-10
    X-10 is the project code name for the Clinton Pile, an early nuclear reactor facility associated with the Manhattan Project.
  • E. Arx
    Arx was the ancient citadel on Rome’s Capitoline Hill, serving as a fortified stronghold and important religious and defensive center of the city.
  • 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: AX 11
Triple: [Citroën AX, trimLevel, AX 11]
Generated description
AX 11 is a specific trim level of the Citroën AX supermini, typically featuring a modestly more powerful engine and upgraded equipment over the base models.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AX 11
Target entity description: AX 11 is a specific trim level of the Citroën AX supermini, typically featuring a modestly more powerful engine and upgraded equipment over the base models.
  • A. AXK
    AXK is the ICAO airline designator assigned to African Express Airways, a regional carrier based in Kenya.
  • B. AXT
    AXT is the three-letter IATA airport code for Akita Airport in Akita Prefecture, Japan.
  • C. AXJ
    AXJ is the IATA airport code for Amakusa Airfield, a regional airport serving the Amakusa Islands in Kumamoto Prefecture, Japan.
  • D. X-10
    X-10 is the project code name for the Clinton Pile, an early nuclear reactor facility associated with the Manhattan Project.
  • E. Arx
    Arx was the ancient citadel on Rome’s Capitoline Hill, serving as a fortified stronghold and important religious and defensive center of the city.
  • 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_69d87f1bb0988190b490d273dbf3fd03 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e2020198908190b56900cbfc53f25c completed April 17, 2026, 9:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff2a7fe308190a9a2ef7815e788c6 completed May 10, 2026, 2:51 a.m.
NEDg Description generation batch_69fff3b25ba081909c396431ace865ac completed May 10, 2026, 2:55 a.m.
NED2 Entity disambiguation (via description) batch_69fff4a2964c8190bfa8c2fa0f934abe completed May 10, 2026, 2:59 a.m.
Created at: April 10, 2026, 5 a.m.