Triple
T15023829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sukkur Airport |
E378155
|
entity |
| Predicate | ICAO code |
P419
|
FINISHED |
| Object | OPSK |
E1134274
|
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: OPSK | Statement: [Sukkur Airport, ICAO code, OPSK]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: OPSK Context triple: [Sukkur Airport, ICAO code, OPSK]
-
A.
OPSK
chosen
OPSK is the ICAO airport code assigned to Sukkur Airport in Pakistan.
-
B.
OPSG
OPSG is a U.S. federal grant program that provides funding to state, local, and tribal law enforcement agencies to enhance border security and cooperation along international land and water borders.
-
C.
OKS
OKS is the abbreviation commonly used for the National Olympic Committee of Serbia, the body responsible for organizing the country’s participation in the Olympic Games.
-
D.
OSO
OSO is the commonly used abbreviation for the Office of SIGINT Operations, a signals intelligence unit within the U.S. National Security Agency.
-
E.
OPST
OPST is the ICAO airport code for Sialkot International Airport in Sialkot, Pakistan.
- 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_69d85cd46b2c819090d054c27787f677 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7de117c8190a1b9fa8d1602057e |
completed | April 15, 2026, 12:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fea5b0bbf4819082e14715bfd6003d |
completed | May 9, 2026, 3:10 a.m. |
Created at: April 10, 2026, 2:56 a.m.