Triple
T107591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles de Gaulle Airport |
E2173
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object |
LFPG
LFPG is the ICAO airport code for Paris Charles de Gaulle Airport, France’s largest and busiest international air hub.
|
E10903
|
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: LFPG | Statement: [Charles de Gaulle Airport, ICAOcode, LFPG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LFPG Context triple: [Charles de Gaulle Airport, ICAOcode, LFPG]
-
A.
LDP
LDP is a common abbreviation for the Liberal Democratic Party, a major political party name used in several countries, most prominently Japan.
-
B.
FSG
FSG is a global sports investment company best known for owning major franchises such as the Boston Red Sox and Liverpool FC.
-
C.
FRS
FRS is the post-nominal title used by Fellows of the Royal Society, denoting distinguished scientists elected to the United Kingdom’s national academy of sciences.
-
D.
.phl
.phl is a proposed or lesser-used internet country code top-level domain associated with the Philippines, distinct from its primary ccTLD, .ph.
-
E.
LU
LU is the two-letter ISO 3166-1 alpha-2 country code assigned to Luxembourg for international identification and data standards.
- 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: LFPG Triple: [Charles de Gaulle Airport, ICAOcode, LFPG]
Generated description
LFPG is the ICAO airport code for Paris Charles de Gaulle Airport, France’s largest and busiest international air hub.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: LFPG Target entity description: LFPG is the ICAO airport code for Paris Charles de Gaulle Airport, France’s largest and busiest international air hub.
-
A.
LDP
LDP is a common abbreviation for the Liberal Democratic Party, a major political party name used in several countries, most prominently Japan.
-
B.
FSG
FSG is a global sports investment company best known for owning major franchises such as the Boston Red Sox and Liverpool FC.
-
C.
FRS
FRS is the post-nominal title used by Fellows of the Royal Society, denoting distinguished scientists elected to the United Kingdom’s national academy of sciences.
-
D.
.phl
.phl is a proposed or lesser-used internet country code top-level domain associated with the Philippines, distinct from its primary ccTLD, .ph.
-
E.
LU
LU is the two-letter ISO 3166-1 alpha-2 country code assigned to Luxembourg for international identification and data standards.
- 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_69a24fcdaeb48190a2d796677e4b3281 |
completed | Feb. 28, 2026, 2:15 a.m. |
| NER | Named-entity recognition | batch_69a256cac6d4819083b50c9c9d95e975 |
completed | Feb. 28, 2026, 2:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a275e81aa48190827b634822e25058 |
completed | Feb. 28, 2026, 4:58 a.m. |
| NEDg | Description generation | batch_69a2772d526881909052faae2b3b9829 |
completed | Feb. 28, 2026, 5:03 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a277a7c6a08190820993e8de80d21a |
completed | Feb. 28, 2026, 5:05 a.m. |
Created at: Feb. 28, 2026, 2:20 a.m.