Triple
T5051660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harju County |
E113798
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Keila
Keila is a small town in northern Estonia known for its historic church, scenic Keila River and waterfall, and role as a local administrative and transport hub.
|
E491585
|
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: Keila | Statement: [Harju County, contains, Keila]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Keila Context triple: [Harju County, contains, Keila]
-
A.
Renaelva
Renaelva is a river in eastern Norway that flows through Hedmark county before joining the larger Glomma river.
-
B.
Kirsha
Kirsha is a central character in Naguib Mahfouz’s novel "Midaq Alley," known as the café owner whose personal life and hidden desires reflect the social and moral tensions of mid-20th-century Cairo.
-
C.
Wakema
Wakema is a town in Myanmar’s Ayeyarwady Region, known as the birthplace of former Burmese Prime Minister U Nu.
-
D.
Kadina
Kadina is a historic copper mining town and one of the main commercial centers on South Australia's Yorke Peninsula.
-
E.
Kynthia
Kynthia is an ancient Greek epithet and form of the name Cynthia, traditionally associated with the moon goddess Artemis and the island of Kynthos (Cynthus).
- 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: Keila Triple: [Harju County, contains, Keila]
Generated description
Keila is a small town in northern Estonia known for its historic church, scenic Keila River and waterfall, and role as a local administrative and transport hub.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Keila Target entity description: Keila is a small town in northern Estonia known for its historic church, scenic Keila River and waterfall, and role as a local administrative and transport hub.
-
A.
Renaelva
Renaelva is a river in eastern Norway that flows through Hedmark county before joining the larger Glomma river.
-
B.
Kirsha
Kirsha is a central character in Naguib Mahfouz’s novel "Midaq Alley," known as the café owner whose personal life and hidden desires reflect the social and moral tensions of mid-20th-century Cairo.
-
C.
Wakema
Wakema is a town in Myanmar’s Ayeyarwady Region, known as the birthplace of former Burmese Prime Minister U Nu.
-
D.
Kadina
Kadina is a historic copper mining town and one of the main commercial centers on South Australia's Yorke Peninsula.
-
E.
Kynthia
Kynthia is an ancient Greek epithet and form of the name Cynthia, traditionally associated with the moon goddess Artemis and the island of Kynthos (Cynthus).
- 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_69bd443aa1f88190abb992d138f2cf42 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7426fc8081908a8227f73168c235 |
completed | March 20, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69beb0fd25c081909ddf2d8eb77f33e7 |
completed | March 21, 2026, 2:53 p.m. |
| NEDg | Description generation | batch_69beb1a445f48190b3318d816830e1a6 |
completed | March 21, 2026, 2:56 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69beb23f789c8190811ee9e43327196c |
completed | March 21, 2026, 2:59 p.m. |
Created at: March 20, 2026, 1:37 p.m.