Triple
T11097280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DG REGIO |
E262407
|
entity |
| Predicate | collaboratesWith |
P37
|
FINISHED |
| Object | DG EMPL |
E262399
|
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: DG EMPL | Statement: [DG REGIO, collaboratesWith, DG EMPL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DG EMPL Context triple: [DG REGIO, collaboratesWith, DG EMPL]
-
A.
DG EMPL
chosen
DG EMPL is the European Commission department responsible for EU policies on employment, social affairs, skills, labour mobility, and social inclusion.
-
B.
EMP
EMP is a Seattle-based museum and cultural institution (now called the Museum of Pop Culture) dedicated to contemporary popular music, science fiction, and pop culture.
-
C.
DG HR
DG HR is the European Commission’s Directorate-General responsible for human resources management, staff policies, and security within the institution.
-
D.
Manpower
Manpower is a 1941 American drama film directed by Raoul Walsh, starring Edward G. Robinson, Marlene Dietrich, and George Raft in a story about rival linemen whose friendship is tested by love and ambition.
-
E.
ADP
ADP is a leading global provider of payroll, human capital management, and HR outsourcing solutions for businesses of all sizes.
- 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_69d6aa9a40d88190a373e2c7e48285db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d79a0a02cc8190a15df663d4860163 |
completed | April 9, 2026, 12:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e42d69c8b4819092614e83e855430e |
completed | April 19, 2026, 1:18 a.m. |
Created at: April 8, 2026, 9:27 p.m.