Triple

T5220989
Position Surface form Disambiguated ID Type / Status
Subject Marina di Campo Airport E117866 entity
Predicate ICAOcode P419 FINISHED
Object LIRJ
LIRJ is the ICAO airport code for Marina di Campo Airport, a small regional airport serving Elba Island in Italy.
 E504133 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: LIRJ | Statement: [Marina di Campo Airport, ICAOcode, LIRJ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LIRJ
Context triple: [Marina di Campo Airport, ICAOcode, LIRJ]
  • A. LIRF
    LIRF is the ICAO airport code for Leonardo da Vinci–Fiumicino Airport, the main international airport serving Rome, Italy.
  • B. JIRP
    JIRP is a long-running glaciological and mountaineering research and education program based on Alaska’s Juneau Icefield.
  • C. LIRA
    LIRA is the ICAO airport code for Ciampino–G. B. Pastine International Airport serving Rome, Italy.
  • D. RIRA
    RIRA is a dissident Irish republican paramilitary organization that split from the Provisional IRA and is known for its armed campaign against British rule in Northern Ireland.
  • E. JLT
    JLT is a large mixed-use waterfront district in Dubai known for its high-rise residential and commercial towers clustered around artificial lakes.
  • 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: LIRJ
Triple: [Marina di Campo Airport, ICAOcode, LIRJ]
Generated description
LIRJ is the ICAO airport code for Marina di Campo Airport, a small regional airport serving Elba Island in Italy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LIRJ
Target entity description: LIRJ is the ICAO airport code for Marina di Campo Airport, a small regional airport serving Elba Island in Italy.
  • A. LIRF
    LIRF is the ICAO airport code for Leonardo da Vinci–Fiumicino Airport, the main international airport serving Rome, Italy.
  • B. JIRP
    JIRP is a long-running glaciological and mountaineering research and education program based on Alaska’s Juneau Icefield.
  • C. LIRA
    LIRA is the ICAO airport code for Ciampino–G. B. Pastine International Airport serving Rome, Italy.
  • D. RIRA
    RIRA is a dissident Irish republican paramilitary organization that split from the Provisional IRA and is known for its armed campaign against British rule in Northern Ireland.
  • E. JLT
    JLT is a large mixed-use waterfront district in Dubai known for its high-rise residential and commercial towers clustered around artificial lakes.
  • 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_69bd4465e03081909bfcfd7113062590 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7ab846548190bcd2c5cd238f6cd9 completed March 20, 2026, 4:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69beeff49d708190a042dfab473a9646 completed March 21, 2026, 7:22 p.m.
NEDg Description generation batch_69bef309c230819094ed6ae3fefe6e5b completed March 21, 2026, 7:35 p.m.
NED2 Entity disambiguation (via description) batch_69bef36c88f4819082931dbe1bb13f89 completed March 21, 2026, 7:37 p.m.
Created at: March 20, 2026, 1:48 p.m.