Triple
T3892545
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wilbur Smith |
E88092
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Gold Mine
"Gold Mine" is a thriller novel by Wilbur Smith that centers on power struggles, greed, and danger in the South African gold mining industry.
|
E397503
|
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: Gold Mine | Statement: [Wilbur Smith, notableWork, Gold Mine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gold Mine Context triple: [Wilbur Smith, notableWork, Gold Mine]
-
A.
Black Gold
"Black Gold" is a song featured on Ry Cooder's 2013 album *Songs Cycled*, known for its blend of roots music and socially conscious themes.
-
B.
Placer
Placer is the former historic name of the town now known as Loomis in Placer County, California.
-
C.
Golden Pan
The Golden Pan is a prestigious literary award recognizing authors whose books have achieved significant commercial success, often marked by high sales milestones.
-
D.
Gold Rush Country
Gold Rush Country is a themed area within the Dreamworld amusement park that recreates a gold-mining frontier atmosphere with related rides and attractions.
-
E.
House of gold
House of gold is a Marian title from the Litany of Loreto that poetically honors the Virgin Mary as a precious, holy dwelling place of God.
- 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: Gold Mine Triple: [Wilbur Smith, notableWork, Gold Mine]
Generated description
"Gold Mine" is a thriller novel by Wilbur Smith that centers on power struggles, greed, and danger in the South African gold mining industry.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gold Mine Target entity description: "Gold Mine" is a thriller novel by Wilbur Smith that centers on power struggles, greed, and danger in the South African gold mining industry.
-
A.
Black Gold
"Black Gold" is a song featured on Ry Cooder's 2013 album *Songs Cycled*, known for its blend of roots music and socially conscious themes.
-
B.
Placer
Placer is the former historic name of the town now known as Loomis in Placer County, California.
-
C.
Golden Pan
The Golden Pan is a prestigious literary award recognizing authors whose books have achieved significant commercial success, often marked by high sales milestones.
-
D.
Gold Rush Country
Gold Rush Country is a themed area within the Dreamworld amusement park that recreates a gold-mining frontier atmosphere with related rides and attractions.
-
E.
House of gold
House of gold is a Marian title from the Litany of Loreto that poetically honors the Virgin Mary as a precious, holy dwelling place of God.
- 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_69aed9466d548190939f5217a23ed4ac |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeecb237748190a4d41b76e8efd0ba |
completed | March 9, 2026, 3:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b51c9484f08190b47eec550e521da5 |
completed | March 14, 2026, 8:30 a.m. |
| NEDg | Description generation | batch_69b51d9295908190a282d9b3f1cbb34c |
completed | March 14, 2026, 8:34 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b51e1d6d988190b2c1a3f42964aaaa |
completed | March 14, 2026, 8:36 a.m. |
Created at: March 9, 2026, 3:21 p.m.