Triple
T15589659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Competition Commission |
E374709
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object |
COMCO
COMCO is the Swiss Competition Commission, the federal authority responsible for enforcing antitrust and competition law in Switzerland.
|
E1165179
|
NE FINISHED |
How this triple was built (4 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: COMCO | Statement: [Competition Commission, shortName, COMCO]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: COMCO Context triple: [Competition Commission, shortName, COMCO]
-
A.
SEMCO
SEMCO is the brand name used by Samsung Electro-Mechanics for its electronic components and related technologies.
-
B.
Scomi Engineering
Scomi Engineering is a Malaysian engineering company known for designing and supplying monorail systems and related urban transport solutions.
-
C.
Comnidyne
Comnidyne is the fictional corporation where Kevin Spacey’s character Dave Harken works as a tyrannical boss in the comedy film "Horrible Bosses."
-
D.
RobCo Industries
RobCo Industries is a prominent pre-war technology corporation in the Fallout universe, best known for producing advanced robotics, terminals, and personal computing devices.
-
E.
Comeng
Comeng is an Australian engineering and rolling stock manufacturing company best known for producing trains and other rail vehicles used across the country.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: COMCO Triple: [Competition Commission, shortName, COMCO]
Generated description
COMCO is the Swiss Competition Commission, the federal authority responsible for enforcing antitrust and competition law in Switzerland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: COMCO Target entity description: COMCO is the Swiss Competition Commission, the federal authority responsible for enforcing antitrust and competition law in Switzerland.
-
A.
SEMCO
SEMCO is the brand name used by Samsung Electro-Mechanics for its electronic components and related technologies.
-
B.
Scomi Engineering
Scomi Engineering is a Malaysian engineering company known for designing and supplying monorail systems and related urban transport solutions.
-
C.
Comnidyne
Comnidyne is the fictional corporation where Kevin Spacey’s character Dave Harken works as a tyrannical boss in the comedy film "Horrible Bosses."
-
D.
RobCo Industries
RobCo Industries is a prominent pre-war technology corporation in the Fallout universe, best known for producing advanced robotics, terminals, and personal computing devices.
-
E.
Comeng
Comeng is an Australian engineering and rolling stock manufacturing company best known for producing trains and other rail vehicles used across the country.
- F. None of above. chosen
Provenance (5 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_69d85cce25008190b13b52745fbd719b |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e4a19708190936118d569f3436d |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff4c53617c8190b4367eee351dc025 |
completed | May 9, 2026, 3:01 p.m. |
| NEDg | Description generation | batch_69ff4d5de6ec8190ab82ac78bb70a432 |
completed | May 9, 2026, 3:06 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff4dd868388190a159618c1fdcf15c |
completed | May 9, 2026, 3:08 p.m. |
Created at: April 10, 2026, 4:11 a.m.