Triple
T8489805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ICANN At-Large Community |
E200938
|
entity |
| Predicate | usesAcronym |
P43
|
FINISHED |
| Object |
At-Large
At-Large is the global community of individual Internet users who participate in ICANN’s policy development and decision-making processes.
|
E737310
|
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: At-Large | Statement: [ICANN At-Large Community, usesAcronym, At-Large]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: At-Large Context triple: [ICANN At-Large Community, usesAcronym, At-Large]
-
A.
Yost
Yost is a surname most notably associated with Fielding H. Yost, the pioneering early 20th-century American college football coach.
-
B.
Arpoador
Arpoador is a famous rocky peninsula and beach area in Rio de Janeiro, Brazil, renowned for its surfing waves and sunset views over the ocean.
-
C.
Anthemous
Anthemous was an ancient region of Macedonia located adjacent to Bottiaea, known from classical Greek geography and history.
-
D.
Arcop
Arcop was a prominent Canadian architectural firm known for its modernist designs and major cultural and institutional projects across Canada.
-
E.
Fadden
Fadden is an Australian federal electoral division in Queensland, represented in the House of Representatives.
- 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: At-Large Triple: [ICANN At-Large Community, usesAcronym, At-Large]
Generated description
At-Large is the global community of individual Internet users who participate in ICANN’s policy development and decision-making processes.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: At-Large Target entity description: At-Large is the global community of individual Internet users who participate in ICANN’s policy development and decision-making processes.
-
A.
Yost
Yost is a surname most notably associated with Fielding H. Yost, the pioneering early 20th-century American college football coach.
-
B.
Arpoador
Arpoador is a famous rocky peninsula and beach area in Rio de Janeiro, Brazil, renowned for its surfing waves and sunset views over the ocean.
-
C.
Anthemous
Anthemous was an ancient region of Macedonia located adjacent to Bottiaea, known from classical Greek geography and history.
-
D.
Arcop
Arcop was a prominent Canadian architectural firm known for its modernist designs and major cultural and institutional projects across Canada.
-
E.
Fadden
Fadden is an Australian federal electoral division in Queensland, represented in the House of Representatives.
- 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_69ca831d7b148190a6e32c1de43ab13b |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe5596f1c8190aead21a245f21c07 |
completed | March 31, 2026, 3:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce3a4e5be48190b5c598123ef75f8b |
completed | April 2, 2026, 9:43 a.m. |
| NEDg | Description generation | batch_69ce3d0323248190a076a209df98c96c |
completed | April 2, 2026, 9:55 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ce3d7909f48190a46f58fca75d7740 |
completed | April 2, 2026, 9:57 a.m. |
Created at: March 30, 2026, 6:13 p.m.