Triple
T14036634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ellinikon International Airport |
E337728
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object |
LGAT
LGAT is the former ICAO airport code for Ellinikon International Airport, the now-closed primary airport that once served Athens, Greece.
|
E1076911
|
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: LGAT | Statement: [Ellinikon International Airport, ICAOcode, LGAT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LGAT Context triple: [Ellinikon International Airport, ICAOcode, LGAT]
-
A.
LGTS
LGTS is the ICAO airport code for Thessaloniki Airport Makedonia, the main international airport serving Thessaloniki, Greece.
-
B.
LGZA
LGZA is the ICAO airport code for Zakynthos International Airport, which serves the Greek island of Zakynthos in the Ionian Sea.
-
C.
LGLE
LGLE is the ICAO airport code for Leros Municipal Airport, a small regional airport serving the Greek island of Leros in the Aegean Sea.
-
D.
LGF.A
LGF.A is the Class A common stock of Lionsgate, a major entertainment company known for producing and distributing films and television series.
-
E.
LETGS
LETGS is a high-resolution X-ray grating spectrometer aboard NASA’s Chandra X-ray Observatory used to disperse and analyze X-ray emissions from cosmic sources.
- 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: LGAT Triple: [Ellinikon International Airport, ICAOcode, LGAT]
Generated description
LGAT is the former ICAO airport code for Ellinikon International Airport, the now-closed primary airport that once served Athens, Greece.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: LGAT Target entity description: LGAT is the former ICAO airport code for Ellinikon International Airport, the now-closed primary airport that once served Athens, Greece.
-
A.
LGTS
LGTS is the ICAO airport code for Thessaloniki Airport Makedonia, the main international airport serving Thessaloniki, Greece.
-
B.
LGZA
LGZA is the ICAO airport code for Zakynthos International Airport, which serves the Greek island of Zakynthos in the Ionian Sea.
-
C.
LGLE
LGLE is the ICAO airport code for Leros Municipal Airport, a small regional airport serving the Greek island of Leros in the Aegean Sea.
-
D.
LGF.A
LGF.A is the Class A common stock of Lionsgate, a major entertainment company known for producing and distributing films and television series.
-
E.
LETGS
LETGS is a high-resolution X-ray grating spectrometer aboard NASA’s Chandra X-ray Observatory used to disperse and analyze X-ray emissions from cosmic sources.
- 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_69d81c664e48819088cbd8f433aeffe5 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de30e312148190a6be0a3258364e6e |
completed | April 14, 2026, 12:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbc339d53c8190a9cd7027a716ff5f |
completed | May 6, 2026, 10:39 p.m. |
| NEDg | Description generation | batch_69fbc6888b648190866c77296625a4c4 |
completed | May 6, 2026, 10:54 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fbc6ead8cc8190b4ae3ba99dc52934 |
completed | May 6, 2026, 10:55 p.m. |
Created at: April 9, 2026, 10:20 p.m.