Triple
T23103653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminal 2 |
E576099
|
entity |
| Predicate | servesAirportIATA |
P119918
|
FINISHED |
| Object | DAC |
—
|
NE NERFINISHED |
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: DAC | Statement: [Terminal 2, servesAirportIATA, DAC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DAC Context triple: [Terminal 2, servesAirportIATA, DAC]
-
A.
DAC
chosen
DAC is the three-letter IATA airport code for Hazrat Shahjalal International Airport serving Dhaka, Bangladesh.
-
B.
DAC
DAC (Districtus Austriae Controllatus) is Austria’s designation for high-quality, region-typical wines produced under strict geographic and production regulations.
-
C.
DAC
The DAC is the main OECD forum where major donor countries coordinate and set standards for international development cooperation and official development assistance.
-
D.
DAC
DAC is the commonly used abbreviation for the Daskalakis Athletic Center, a major sports and recreation facility at Drexel University in Philadelphia.
-
E.
ADC
ADC is a former U.S. federal assistance program that provided financial support to low-income families with dependent children.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18deaacbc8190a97e64e1cf39cdd6 |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:58 p.m.