Triple
T9275059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tartu railway station |
E222924
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object |
Tapa
Tapa is a town in northern Estonia that serves as a key railway junction and transport hub in the country’s rail network.
|
E787950
|
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: Tapa | Statement: [Tartu railway station, connectsTo, Tapa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tapa Context triple: [Tartu railway station, connectsTo, Tapa]
-
A.
Tapalpa
Tapalpa is a picturesque mountain town in the Mexican state of Jalisco, known for its colonial architecture, pine forests, and outdoor recreation.
-
B.
Tappara
Tappara is a prominent professional ice hockey club from Tampere, Finland, known as one of the most successful and historic teams in the Finnish Liiga.
-
C.
Tepa
Tepa is the colloquial demonym for residents of Tepatitlán de Morelos, a city in the Mexican state of Jalisco.
-
D.
Tuktukan
Tuktukan is a barangay (village-level administrative division) in the city of Taguig in Metro Manila, Philippines.
-
E.
Tepiman
Tepiman is a subgroup of Uto-Aztecan languages spoken primarily in the southwestern United States and northern Mexico, including languages such as O'odham and Tepehuán.
- 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: Tapa Triple: [Tartu railway station, connectsTo, Tapa]
Generated description
Tapa is a town in northern Estonia that serves as a key railway junction and transport hub in the country’s rail network.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tapa Target entity description: Tapa is a town in northern Estonia that serves as a key railway junction and transport hub in the country’s rail network.
-
A.
Tapalpa
Tapalpa is a picturesque mountain town in the Mexican state of Jalisco, known for its colonial architecture, pine forests, and outdoor recreation.
-
B.
Tappara
Tappara is a prominent professional ice hockey club from Tampere, Finland, known as one of the most successful and historic teams in the Finnish Liiga.
-
C.
Tepa
Tepa is the colloquial demonym for residents of Tepatitlán de Morelos, a city in the Mexican state of Jalisco.
-
D.
Tuktukan
Tuktukan is a barangay (village-level administrative division) in the city of Taguig in Metro Manila, Philippines.
-
E.
Tepiman
Tepiman is a subgroup of Uto-Aztecan languages spoken primarily in the southwestern United States and northern Mexico, including languages such as O'odham and Tepehuán.
- 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_69ca841ffe208190aa7bcffbef2f8379 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd078a045c8190b2c4d1ec64b932ad |
completed | April 1, 2026, 11:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d09c3dd140819099fc0e95c4d48ba9 |
completed | April 4, 2026, 5:06 a.m. |
| NEDg | Description generation | batch_69d09cf1f2f48190b53e062c3eb4565d |
completed | April 4, 2026, 5:09 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d09d9739d48190ac3b240390f36c38 |
completed | April 4, 2026, 5:11 a.m. |
Created at: March 30, 2026, 7:34 p.m.