Triple
T15310312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Archer Daniels Midland |
E366016
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | ADM |
E1150656
|
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: ADM | Statement: [Archer Daniels Midland, shortName, ADM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ADM Context triple: [Archer Daniels Midland, shortName, ADM]
-
A.
ADM
chosen
ADM is the stock ticker symbol for Archer Daniels Midland, a major American global food processing and commodities trading corporation.
-
B.
ADM
ADM is a creative academic institution focused on education and research in the fields of art, design, and media.
-
C.
ADM
ADM is the abbreviated name for Aéroports de Montréal, the authority that manages the main international airports serving the Montreal region in Canada.
-
D.
ADM(IM)
ADM(IM) is the abbreviated designation for the Assistant Deputy Minister responsible for information management within a governmental or organizational structure.
-
E.
ARAM
ARAM is a fast-paced League of Legends game mode where teams fight continuously on a single narrow bridge-like map with randomly assigned champions.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03cd176708190b0f6ba17aed92f8e |
completed | April 16, 2026, 1:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff01e70a308190a7d6b91178c39bd3 |
completed | May 9, 2026, 9:44 a.m. |
Created at: April 10, 2026, 3:16 a.m.