Triple
T11071675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MNL |
E261759
|
entity |
| Predicate | icaoCode |
P419
|
FINISHED |
| Object | RPLL |
E261760
|
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: RPLL | Statement: [MNL, icaoCode, RPLL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RPLL Context triple: [MNL, icaoCode, RPLL]
-
A.
RPLL
chosen
RPLL is the ICAO airport code for Ninoy Aquino International Airport, the main international gateway serving Metro Manila in the Philippines.
-
B.
EPLL
EPLL is the ICAO airport code for Łódź Władysław Reymont Airport in Łódź, Poland.
-
C.
RRTL
RRTL is the stock ticker symbol for RTL Group, a leading European entertainment company specializing in television, radio, and digital media.
-
D.
RLC
RLC is the Royal Logistic Corps, a branch of the British Army responsible for providing logistics support including supply, transport, and distribution.
-
E.
RL
RL is the commonly used acronym for the U.S. Department of Energy’s Richland Operations Office, which oversees environmental cleanup and related activities at the Hanford Site in Washington State.
- 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_69d6aa9983c08190b0ef61603b69feac |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7994bbb30819090410bd3d0fde33c |
completed | April 9, 2026, 12:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3c8bfb0c88190be27f5ce09b02c8b |
completed | April 18, 2026, 6:09 p.m. |
Created at: April 8, 2026, 9:26 p.m.