Triple
T9033866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clark Air Base |
E216439
|
entity |
| Predicate | hasICAOcode |
P419
|
FINISHED |
| Object | RPLC |
E597148
|
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: RPLC | Statement: [Clark Air Base, hasICAOcode, RPLC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RPLC Context triple: [Clark Air Base, hasICAOcode, RPLC]
-
A.
RPLC
chosen
RPLC is the ICAO airport code for Clark International Airport, a major aviation hub in the Philippines located on the site of the former U.S. Clark Air Base.
-
B.
RPL
RPL is the top professional football (soccer) league in Russia, featuring the country’s highest-level clubs in national competition.
-
C.
RLC
RLC is the Royal Logistic Corps, a branch of the British Army responsible for providing logistics support including supply, transport, and distribution.
-
D.
RPL programming language
RPL is a stack-based, reverse Polish Lisp-like programming language developed by Hewlett-Packard for its graphing calculators, combining features of RPN and structured programming.
-
E.
RLP
RLP is the vehicle registration code used for the German federal state of Rhineland-Palatinate.
- 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_69ca83d10b608190b2b2f8e0a7faaf14 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc6aa248bc8190a55cfc2a5306ab20 |
completed | April 1, 2026, 12:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfdbc9c6e08190aa71d84316afc6d5 |
completed | April 3, 2026, 3:24 p.m. |
Created at: March 30, 2026, 7:08 p.m.