Triple
T18701241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anhui University |
E457253
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | AHD |
E457253
|
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: AHD | Statement: [Anhui University, abbreviation, AHD]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AHD Context triple: [Anhui University, abbreviation, AHD]
-
A.
AHD
chosen
AHD is the abbreviated name commonly used for Anhui University, a major comprehensive public university in Anhui Province, China.
-
B.
AHD
AHD is the National Rail station code for Ashtead railway station in Surrey, England.
-
C.
ANA HD
ANA HD is a Japanese aviation holding company that owns and operates All Nippon Airways and related air transport and travel businesses.
-
D.
AHT
AHT is the IATA airport code for the airport serving Anholt, a small Danish island in the Kattegat Sea.
-
E.
HDX
HDX is an open humanitarian data platform that enables organizations to share, find, and use data for crisis preparedness and response.
- 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_69d8d392aad081909fe31aa03e6e97d1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5671391048190bba7606f4283ca09 |
completed | April 19, 2026, 11:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a052b36caa88190a6302741aca9eb00 |
completed | May 14, 2026, 1:53 a.m. |
Created at: April 10, 2026, 11:49 a.m.