Triple
T18685334
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Dancer |
E456844
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object |
Soko
Soko is a French singer-songwriter and actress known for her emotionally raw music and roles in independent films.
|
E1337049
|
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: Soko | Statement: [The Dancer, stars, Soko]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Soko Context triple: [The Dancer, stars, Soko]
-
A.
Mercara
Mercara is the former anglicized name for Madikeri, a hill town and district headquarters in the Coorg (Kodagu) region of Karnataka, India.
-
B.
Mosina
Mosina is an alternative name for Vurës, a language spoken on the island of Vanua Lava in Vanuatu.
-
C.
Landi Kotal
Landi Kotal is a town in Pakistan’s Khyber District, historically significant as a key trading and military post near the Khyber Pass on the route to Afghanistan.
-
D.
Sako
Sako is a Finnish firearms manufacturer renowned for its high-quality rifles and precision engineering, operating as a subsidiary of Beretta.
-
E.
Sako
Sako is a surname most prominently associated with Louis Raphaël I Sako, the Chaldean Catholic Patriarch of Babylon and a leading figure in the modern Iraqi Christian community.
- 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: Soko Triple: [The Dancer, stars, Soko]
Generated description
Soko is a French singer-songwriter and actress known for her emotionally raw music and roles in independent films.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Soko Target entity description: Soko is a French singer-songwriter and actress known for her emotionally raw music and roles in independent films.
-
A.
Mercara
Mercara is the former anglicized name for Madikeri, a hill town and district headquarters in the Coorg (Kodagu) region of Karnataka, India.
-
B.
Mosina
Mosina is an alternative name for Vurës, a language spoken on the island of Vanua Lava in Vanuatu.
-
C.
Landi Kotal
Landi Kotal is a town in Pakistan’s Khyber District, historically significant as a key trading and military post near the Khyber Pass on the route to Afghanistan.
-
D.
Sako
Sako is a Finnish firearms manufacturer renowned for its high-quality rifles and precision engineering, operating as a subsidiary of Beretta.
-
E.
Sako
Sako is a surname most prominently associated with Louis Raphaël I Sako, the Chaldean Catholic Patriarch of Babylon and a leading figure in the modern Iraqi Christian community.
- 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_69d8d391eb488190ac2e9abf5bf255e4 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e55b2c58188190b906c9ab080a76ff |
completed | April 19, 2026, 10:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05235a0d488190a3a5d01822f45e08 |
completed | May 14, 2026, 1:20 a.m. |
| NEDg | Description generation | batch_6a05248c12d88190abb947a37b7d180c |
completed | May 14, 2026, 1:25 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a052523e1588190a365dc093d8352a1 |
completed | May 14, 2026, 1:28 a.m. |
Created at: April 10, 2026, 11:49 a.m.