Triple
T8037247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runway A 16L/34R |
E187137
|
entity |
| Predicate | hasICAOCodeOfAirport |
P419
|
FINISHED |
| Object | RJTT |
E186915
|
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: RJTT | Statement: [Runway A 16L/34R, hasICAOCodeOfAirport, RJTT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RJTT Context triple: [Runway A 16L/34R, hasICAOCodeOfAirport, RJTT]
-
A.
RJTT
chosen
RJTT is the ICAO airport code for Tokyo International Airport, commonly known as Haneda Airport, one of Japan’s primary airports serving the Tokyo metropolitan area.
-
B.
RJT
RJT is the station code for Rajkot Junction, a major railway station serving the city of Rajkot in Gujarat, India.
-
C.
RJT
RJT is the IATA airport code assigned to Iruma Air Base, a military airfield in Saitama Prefecture, Japan.
-
D.
JTTN
JTTN is the station code for Jorhat Town railway station, a rail transport hub serving the city of Jorhat in Assam, India.
-
E.
RJTM
RJTM is the ICAO airport code assigned to Iruma Air Base, a Japan Air Self-Defense Force installation in Saitama Prefecture, Japan.
- 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_69ca82ae2d1081909dbfee42b41db419 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3f188e1c8190b92760c91d31f2df |
completed | March 31, 2026, 3:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc93bc11108190a34a35d0022f4bfd |
completed | April 1, 2026, 3:40 a.m. |
Created at: March 30, 2026, 5:22 p.m.