Triple
T18905779
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Federal-Mogul |
E462457
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object |
ANCO
ANCO is a well-known automotive aftermarket brand specializing in windshield wiper blades and related visibility products.
|
E1348856
|
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: ANCO | Statement: [Federal-Mogul, brand, ANCO]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ANCO Context triple: [Federal-Mogul, brand, ANCO]
-
A.
anacos
Anacos are traditional wrap-around woolen skirts worn by Indigenous Otavalo women in the Andean region of Ecuador.
-
B.
ANO
ANO is the ICAO airline designator assigned to Airnorth, a regional airline based in Australia.
-
C.
ASNC
ASNC is a professional medical society dedicated to advancing the science, education, and clinical practice of nuclear cardiology.
-
D.
ANCYL
ANCYL is the youth wing of South Africa’s African National Congress, historically known for mobilizing young people in the anti-apartheid struggle and contemporary politics.
-
E.
CO-ANT
CO-ANT is the administrative region code for the Antioquia Department in Colombia, used to identify municipalities such as Turbo within that jurisdiction.
- 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: ANCO Triple: [Federal-Mogul, brand, ANCO]
Generated description
ANCO is a well-known automotive aftermarket brand specializing in windshield wiper blades and related visibility products.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: ANCO Target entity description: ANCO is a well-known automotive aftermarket brand specializing in windshield wiper blades and related visibility products.
-
A.
anacos
Anacos are traditional wrap-around woolen skirts worn by Indigenous Otavalo women in the Andean region of Ecuador.
-
B.
ANO
ANO is the ICAO airline designator assigned to Airnorth, a regional airline based in Australia.
-
C.
ASNC
ASNC is a professional medical society dedicated to advancing the science, education, and clinical practice of nuclear cardiology.
-
D.
ANCYL
ANCYL is the youth wing of South Africa’s African National Congress, historically known for mobilizing young people in the anti-apartheid struggle and contemporary politics.
-
E.
CO-ANT
CO-ANT is the administrative region code for the Antioquia Department in Colombia, used to identify municipalities such as Turbo within that jurisdiction.
- 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_69d8dcfd05bc819088903cca13cc2846 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c52cc9cc8190ac489d36e51693c8 |
completed | April 20, 2026, 6:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0582bf4f9481908098c8d405225553 |
completed | May 14, 2026, 8:07 a.m. |
| NEDg | Description generation | batch_6a05899f7a008190a9b0324f403f09ac |
completed | May 14, 2026, 8:36 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a058a1028288190b9fddb9b6b123651 |
completed | May 14, 2026, 8:38 a.m. |
Created at: April 10, 2026, 11:58 a.m.