Triple
T18572478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Utusan Melayu |
E453902
|
entity |
| Predicate | hasCompetitor |
P1375
|
FINISHED |
| Object |
Berita Harian
Berita Harian is a major Malay-language daily newspaper in Malaysia known for its national news coverage and wide readership.
|
E1331385
|
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: Berita Harian | Statement: [Utusan Melayu, hasCompetitor, Berita Harian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Berita Harian Context triple: [Utusan Melayu, hasCompetitor, Berita Harian]
-
A.
Harian Rakjat
Harian Rakjat was the official newspaper of the Indonesian Communist Party, serving as a key propaganda and information outlet in mid-20th-century Indonesia.
-
B.
Cotidianul newspaper
Cotidianul newspaper is a Romanian daily publication known for its independent, often critical journalism and cultural commentary.
-
C.
Jakarta Mail
Jakarta Mail is the Jakarta EE specification that defines a standard API for creating, sending, and receiving email in Java applications.
-
D.
The Daily
The Daily is Statistics Canada’s official online publication that provides timely statistical news, analysis, and key data releases about Canada’s economy, society, and environment.
-
E.
The Evening News
The Evening News is a television newscast program that provides daily coverage of current events, politics, and major stories of public interest.
- 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: Berita Harian Triple: [Utusan Melayu, hasCompetitor, Berita Harian]
Generated description
Berita Harian is a major Malay-language daily newspaper in Malaysia known for its national news coverage and wide readership.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Berita Harian Target entity description: Berita Harian is a major Malay-language daily newspaper in Malaysia known for its national news coverage and wide readership.
-
A.
Harian Rakjat
Harian Rakjat was the official newspaper of the Indonesian Communist Party, serving as a key propaganda and information outlet in mid-20th-century Indonesia.
-
B.
Cotidianul newspaper
Cotidianul newspaper is a Romanian daily publication known for its independent, often critical journalism and cultural commentary.
-
C.
Jakarta Mail
Jakarta Mail is the Jakarta EE specification that defines a standard API for creating, sending, and receiving email in Java applications.
-
D.
The Daily
The Daily is Statistics Canada’s official online publication that provides timely statistical news, analysis, and key data releases about Canada’s economy, society, and environment.
-
E.
The Evening News
The Evening News is a television newscast program that provides daily coverage of current events, politics, and major stories of public interest.
- 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_69d8d38974308190a9174430ef256b73 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53b032488819098de683bb5c42c4b |
completed | April 19, 2026, 8:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a04f886f2e88190bf01061cb793c0ab |
completed | May 13, 2026, 10:17 p.m. |
| NEDg | Description generation | batch_6a04f9511eb08190952be765862cd1ab |
completed | May 13, 2026, 10:21 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a04f9dd338881908b300bab7947f736 |
completed | May 13, 2026, 10:23 p.m. |
Created at: April 10, 2026, 11:43 a.m.