Triple
T23387281
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richards Bay Airport |
E593917
|
entity |
| Predicate | ICAO code |
P419
|
FINISHED |
| Object |
FARB
FARB is the ICAO airport code for Richards Bay Airport in South Africa, a regional airport serving the city of Richards Bay and its surrounding areas.
|
E1582262
|
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: FARB | Statement: [Richards Bay Airport, ICAO code, FARB]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FARB Context triple: [Richards Bay Airport, ICAO code, FARB]
-
A.
FAR
FAR is the acronym for Cuba’s national military organization, the Revolutionary Armed Forces.
-
B.
FAR
FAR is the commonly used abbreviation for the Intergovernmental Panel on Climate Change’s First Assessment Report, a foundational scientific evaluation of climate change published in 1990.
-
C.
FAR
FAR is the IATA airport code for Hector International Airport serving Fargo, North Dakota.
-
D.
FAR
FAR is a contemporary dance work by British choreographer Wayne McGregor, known for its innovative fusion of technology, complex movement vocabulary, and exploration of the relationship between the body and scientific ideas.
-
E.
FAR
FAR is the primary set of rules governing the acquisition process and procurement of goods and services by U.S. federal government agencies.
- 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: FARB Triple: [Richards Bay Airport, ICAO code, FARB]
Generated description
FARB is the ICAO airport code for Richards Bay Airport in South Africa, a regional airport serving the city of Richards Bay and its surrounding areas.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: FARB Target entity description: FARB is the ICAO airport code for Richards Bay Airport in South Africa, a regional airport serving the city of Richards Bay and its surrounding areas.
-
A.
FAR
FAR is the IATA airport code for Hector International Airport serving Fargo, North Dakota.
-
B.
FAR
FAR is the primary set of rules governing the acquisition process and procurement of goods and services by U.S. federal government agencies.
-
C.
FAR
FAR is the acronym for Cuba’s national military organization, the Revolutionary Armed Forces.
-
D.
FAR
FAR is the commonly used abbreviation for the Intergovernmental Panel on Climate Change’s First Assessment Report, a foundational scientific evaluation of climate change published in 1990.
-
E.
FAR
FAR is a contemporary dance work by British choreographer Wayne McGregor, known for its innovative fusion of technology, complex movement vocabulary, and exploration of the relationship between the body and scientific ideas.
- 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_69e25d2754fc819085deea939bde60ab |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a498fd08819085e90a872d9d0c7a |
completed | April 29, 2026, 6:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c5de999488190be021920241b7f25 |
completed | May 19, 2026, 12:56 p.m. |
| NEDg | Description generation | batch_6a0c5e7eb7b481908b3cece1823cf785 |
completed | May 19, 2026, 12:58 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c5eef81e48190b62da26fb8d65223 |
completed | May 19, 2026, 1 p.m. |
Created at: April 17, 2026, 5:35 p.m.