Triple
T16284350
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Directorate of Plans |
E395349
|
entity |
| Predicate | officialAbbreviation |
P3776
|
FINISHED |
| Object | DDP |
E1204475
|
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: DDP | Statement: [Directorate of Plans, officialAbbreviation, DDP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DDP Context triple: [Directorate of Plans, officialAbbreviation, DDP]
-
A.
DDP
DDP is a network protocol used in AppleTalk for connectionless, best-effort delivery of datagram packets between devices.
-
B.
DDP
chosen
DDP was the former name of the CIA’s clandestine operations branch, responsible for covert action and espionage during much of the Cold War.
-
C.
DDP
DDP was a liberal political party in the Weimar Republic that advocated democratic reforms, civil liberties, and a parliamentary system in post–World War I Germany.
-
D.
DPP
DPP is the Maryland state agency responsible for supervising individuals on parole and probation and supporting their reintegration into the community.
-
E.
DPP
DPP is the main public transport operator in Prague, responsible for running the city’s metro, trams, and buses.
- 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_69d87f22c7248190a54c949738441e2e |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e24912c5808190a0d9c9f491315068 |
completed | April 17, 2026, 2:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a001f93240881909d0beaddc92f0ad5 |
completed | May 10, 2026, 6:02 a.m. |
Created at: April 10, 2026, 5:05 a.m.