Triple
T22393121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Praying Mantis |
E553555
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object |
Hans in ’t Zandt
Hans in ’t Zandt is a member of the band Praying Mantis, contributing to the group’s melodic hard rock and heavy metal sound.
|
E1534343
|
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: Hans in ’t Zandt | Statement: [Praying Mantis, hasMember, Hans in ’t Zandt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hans in ’t Zandt Context triple: [Praying Mantis, hasMember, Hans in ’t Zandt]
-
A.
Hans Bonte
Hans Bonte is a Belgian politician known for serving as the mayor of Vilvoorde and as a member of the federal parliament.
-
B.
Wiet van Houten
Wiet van Houten is a fictional character from the long-running Dutch soap opera "Goede tijden, slechte tijden," known for her complex personal relationships and dramatic storylines.
-
C.
Jan Kempdorp
Jan Kempdorp is a small agricultural and service town in South Africa’s Northern Cape province.
-
D.
Foppe de Haan
Foppe de Haan is a Dutch football manager best known for his long and influential tenure at SC Heerenveen and for coaching the Netherlands U21 team to multiple European Championship titles.
-
E.
Willem de Zwaan
Willem de Zwaan was an architect known for designing the Paul Kruger statue.
- 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: Hans in ’t Zandt Triple: [Praying Mantis, hasMember, Hans in ’t Zandt]
Generated description
Hans in ’t Zandt is a member of the band Praying Mantis, contributing to the group’s melodic hard rock and heavy metal sound.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hans in ’t Zandt Target entity description: Hans in ’t Zandt is a member of the band Praying Mantis, contributing to the group’s melodic hard rock and heavy metal sound.
-
A.
Hans Bonte
Hans Bonte is a Belgian politician known for serving as the mayor of Vilvoorde and as a member of the federal parliament.
-
B.
Wiet van Houten
Wiet van Houten is a fictional character from the long-running Dutch soap opera "Goede tijden, slechte tijden," known for her complex personal relationships and dramatic storylines.
-
C.
Jan Kempdorp
Jan Kempdorp is a small agricultural and service town in South Africa’s Northern Cape province.
-
D.
Foppe de Haan
Foppe de Haan is a Dutch football manager best known for his long and influential tenure at SC Heerenveen and for coaching the Netherlands U21 team to multiple European Championship titles.
-
E.
Willem de Zwaan
Willem de Zwaan was an architect known for designing the Paul Kruger statue.
- 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_69e11e4cf87c8190a1ff474daec326b7 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1585ce39c819082b62e7f2e297d9b |
completed | April 29, 2026, 1:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0ae9c4dbe08190a85269a922ff23d1 |
completed | May 18, 2026, 10:28 a.m. |
| NEDg | Description generation | batch_6a0aea9aad5c81908fca5ea2b594effb |
completed | May 18, 2026, 10:31 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0aeb4ce6d48190ac9281afb7b43391 |
completed | May 18, 2026, 10:34 a.m. |
Created at: April 16, 2026, 8:45 p.m.