Triple
T12272103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KTLH |
E292495
|
entity |
| Predicate | FAAcode |
P420
|
FINISHED |
| Object | TLH |
E292494
|
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: TLH | Statement: [KTLH, FAAcode, TLH]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TLH Context triple: [KTLH, FAAcode, TLH]
-
A.
TLH
chosen
TLH is the IATA airport code for Tallahassee International Airport, the primary commercial airport serving Florida’s state capital.
-
B.
THLCH
THLCH is the UN/LOCODE identifier for the major deep-sea commercial port of Laem Chabang in Thailand.
-
C.
TLG
TLG is the abbreviation for the Technical Liaison Group, a coordinating body that facilitates communication and collaboration among various technical standards organizations.
-
D.
TLK
TLK is a category of long-distance passenger trains in Poland operated by PKP Intercity, typically offering budget-friendly intercity connections.
-
E.
TLO
TLO, also known as Dario Wünsch, is a German professional StarCraft II player renowned for his creative strategies and long-standing presence in the competitive scene.
- 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_69d6ab6856488190b5d31178d5015f8e |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91cee7158819093fff74db6867896 |
completed | April 10, 2026, 3:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63461cacc81909958fbd745e5d065 |
completed | May 2, 2026, 5:29 p.m. |
Created at: April 8, 2026, 9:52 p.m.