Triple
T8736513
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runway 16R/34L |
E207398
|
entity |
| Predicate | airportIATA |
P418
|
FINISHED |
| Object | NRT |
E190904
|
NE FINISHED |
How this triple was built (2 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: NRT | Statement: [Runway 16R/34L, airportIATA, NRT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NRT Context triple: [Runway 16R/34L, airportIATA, NRT]
-
A.
NRT
chosen
NRT is the three-letter IATA airport code for Narita International Airport, a major international gateway serving the Tokyo metropolitan area in Japan.
-
B.
NR
NR is the two-letter ISO 3166-1 alpha-2 country code assigned to the Republic of Nauru.
-
C.
NR
NR is the standard abbreviation for National Rail, the collective network of passenger railway services in Great Britain.
-
D.
NR
NR is the common abbreviation for New Relic, a cloud-based observability and application performance monitoring platform used by developers and IT operations teams.
-
E.
NR
NR is the radio access technology standard defined by 3GPP for fifth-generation (5G) mobile networks, enabling high-speed, low-latency wireless communication.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca835a03a081909d4d4cd01a18c9fb |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5d44275881909f7eb40b24180294 |
completed | March 31, 2026, 11:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf42bd840081908074e9d322a15b68 |
completed | April 3, 2026, 4:31 a.m. |
Created at: March 30, 2026, 6:38 p.m.