Triple
T16828355
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Republic Party |
E409079
|
entity |
| Predicate | hadMember |
P5021
|
FINISHED |
| Object |
Vause Raw
Vause Raw is a South African politician who served as a member of the New Republic Party during the late apartheid era.
|
E1235399
|
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: Vause Raw | Statement: [New Republic Party, hadMember, Vause Raw]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vause Raw Context triple: [New Republic Party, hadMember, Vause Raw]
-
A.
Vuse
Vuse is an electronic cigarette and vaping product brand owned by British American Tobacco, known for its range of nicotine e-liquids and devices.
-
B.
Vagaus
Vagaus is a character in Antonio Vivaldi’s sacred oratorio "Juditha triumphans," typically portrayed as the loyal and conflicted servant of the Assyrian general Holofernes.
-
C.
Varkaus
Varkaus is a small industrial town and municipality in the Northern Savonia region of eastern Finland, known for its paper and wood-processing industries.
-
D.
Voyce
Voyce is a music producer known for working on the track "Room for Improvement."
-
E.
Vow Wow
Vow Wow is a Japanese hard rock and heavy metal band that gained international recognition in the 1980s for its powerful sound and English-language releases.
- 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: Vause Raw Triple: [New Republic Party, hadMember, Vause Raw]
Generated description
Vause Raw is a South African politician who served as a member of the New Republic Party during the late apartheid era.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Vause Raw Target entity description: Vause Raw is a South African politician who served as a member of the New Republic Party during the late apartheid era.
-
A.
Vuse
Vuse is an electronic cigarette and vaping product brand owned by British American Tobacco, known for its range of nicotine e-liquids and devices.
-
B.
Vagaus
Vagaus is a character in Antonio Vivaldi’s sacred oratorio "Juditha triumphans," typically portrayed as the loyal and conflicted servant of the Assyrian general Holofernes.
-
C.
Varkaus
Varkaus is a small industrial town and municipality in the Northern Savonia region of eastern Finland, known for its paper and wood-processing industries.
-
D.
Voyce
Voyce is a music producer known for working on the track "Room for Improvement."
-
E.
Vow Wow
Vow Wow is a Japanese hard rock and heavy metal band that gained international recognition in the 1980s for its powerful sound and English-language releases.
- 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_69d88394566c8190b3dcbdc72935f7fa |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b3151350819097b1c375e6df8986 |
completed | April 18, 2026, 4:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00b2a0ac148190a7a7edebcb67c040 |
completed | May 10, 2026, 4:30 p.m. |
| NEDg | Description generation | batch_6a00b35ea8f88190ae33e8a2f906d133 |
completed | May 10, 2026, 4:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00b3d14b3c819081f435777f47eca3 |
completed | May 10, 2026, 4:35 p.m. |
Created at: April 10, 2026, 5:23 a.m.