Triple
T1840106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PGUA |
E41156
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object | UAM |
E41155
|
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: UAM | Statement: [PGUA, IATAcode, UAM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UAM Context triple: [PGUA, IATAcode, UAM]
-
A.
UAM
chosen
UAM is the IATA airport code for Andersen Air Force Base, a major United States Air Force installation on Guam.
-
B.
UAK
UAK was the temporary currency code used for the Ukrainian karbovanets, a transitional currency of Ukraine in the early 1990s before the introduction of the hryvnia.
-
C.
UCA
UCA is the Unicode Collation Algorithm, a Unicode standard that defines a language-independent method for ordering and comparing Unicode text.
-
D.
AMU
AMU is the commonly used abbreviation for Aix-Marseille University, a major public research university in southern France.
-
E.
AMU
The AMU, or Arab Maghreb Union, is a regional organization that promotes economic and political cooperation among North African Maghreb countries.
- 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_69a88647f9388190909bc36e795bdaec |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb03b3eb08190ae68d8476fc89c7f |
completed | March 7, 2026, 4:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69add1c482908190b940497fc5d5db60 |
completed | March 8, 2026, 7:45 p.m. |
Created at: March 4, 2026, 7:33 p.m.