Triple
T17311732
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sontarans |
E420315
|
entity |
| Predicate | notableMember |
P10
|
FINISHED |
| Object |
Styre
Styre is a ruthless Sontaran officer from the Doctor Who universe, known for conducting brutal experiments on humans in the serial "The Sontaran Experiment."
|
E1261448
|
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: Styre | Statement: [Sontarans, notableMember, Styre]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Styre Context triple: [Sontarans, notableMember, Styre]
-
A.
Styra
Styra is a coastal town on the island of Euboea in Greece, known for its proximity to the South Euboean Gulf and its scenic seaside setting.
-
B.
Styr
Styr is a river in Eastern Europe that flows through Ukraine and Belarus as a tributary of the Pripyat River.
-
C.
Styr
Styr is the Magnar of Thenn, a fierce wildling leader who commands the Thenn warriors during the assault on the Wall in the Game of Thrones universe.
-
D.
Steng
Steng is the family name of Austrian actor and director Klaus Maria Brandauer, known for his acclaimed performances in European cinema and Hollywood films.
-
E.
Ministerraad
De Ministerraad is het hoogste besluitvormende orgaan van de Nederlandse regering, bestaande uit alle ministers die gezamenlijk het regeringsbeleid bepalen.
- 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: Styre Triple: [Sontarans, notableMember, Styre]
Generated description
Styre is a ruthless Sontaran officer from the Doctor Who universe, known for conducting brutal experiments on humans in the serial "The Sontaran Experiment."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Styre Target entity description: Styre is a ruthless Sontaran officer from the Doctor Who universe, known for conducting brutal experiments on humans in the serial "The Sontaran Experiment."
-
A.
Styra
Styra is a coastal town on the island of Euboea in Greece, known for its proximity to the South Euboean Gulf and its scenic seaside setting.
-
B.
Styr
Styr is the Magnar of Thenn, a fierce wildling leader who commands the Thenn warriors during the assault on the Wall in the Game of Thrones universe.
-
C.
Styr
Styr is a river in Eastern Europe that flows through Ukraine and Belarus as a tributary of the Pripyat River.
-
D.
Steng
Steng is the family name of Austrian actor and director Klaus Maria Brandauer, known for his acclaimed performances in European cinema and Hollywood films.
-
E.
Ministerraad
De Ministerraad is het hoogste besluitvormende orgaan van de Nederlandse regering, bestaande uit alle ministers die gezamenlijk het regeringsbeleid bepalen.
- 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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e439993bac8190a72f6af529bd7cce |
completed | April 19, 2026, 2:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0180e5043081908f31c2434e9b9647 |
completed | May 11, 2026, 7:10 a.m. |
| NEDg | Description generation | batch_6a0182e466e8819096f61fb74d4147c5 |
completed | May 11, 2026, 7:19 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a01840ddbb08190a542faba4ca26e5a |
completed | May 11, 2026, 7:23 a.m. |
Created at: April 10, 2026, 5:43 a.m.