Triple
T13057579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Leyte |
E327617
|
entity |
| Predicate | containsCity |
P294
|
FINISHED |
| Object |
Tabontabon
Tabontabon is a small municipality in the province of Leyte in the Eastern Visayas region of the Philippines.
|
E1018120
|
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: Tabontabon | Statement: [Northern Leyte, containsCity, Tabontabon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tabontabon Context triple: [Northern Leyte, containsCity, Tabontabon]
-
A.
Maromokotro
Maromokotro is the tallest mountain in Madagascar, located in the island’s northern highlands.
-
B.
Tambolaka
Tambolaka is a town on the Indonesian island of Sumba that serves as an important local hub with an airport and access point for exploring the island.
-
C.
Pararaton
Pararaton is a Javanese historical chronicle, also known as the "Book of Kings," that narrates the legendary and political history of the Singhasari and Majapahit kingdoms in Indonesia.
-
D.
Hatosy
Hatosy is the surname of American actor and director Shawn Hatosy, known for his roles in film and television dramas.
-
E.
Baniva
Baniva is an alternate name for the Baniwa language, an Arawakan language spoken by Indigenous communities in the northwest Amazon region of Brazil, Colombia, and Venezuela.
- 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: Tabontabon Triple: [Northern Leyte, containsCity, Tabontabon]
Generated description
Tabontabon is a small municipality in the province of Leyte in the Eastern Visayas region of the Philippines.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tabontabon Target entity description: Tabontabon is a small municipality in the province of Leyte in the Eastern Visayas region of the Philippines.
-
A.
Maromokotro
Maromokotro is the tallest mountain in Madagascar, located in the island’s northern highlands.
-
B.
Tambolaka
Tambolaka is a town on the Indonesian island of Sumba that serves as an important local hub with an airport and access point for exploring the island.
-
C.
Pararaton
Pararaton is a Javanese historical chronicle, also known as the "Book of Kings," that narrates the legendary and political history of the Singhasari and Majapahit kingdoms in Indonesia.
-
D.
Hatosy
Hatosy is the surname of American actor and director Shawn Hatosy, known for his roles in film and television dramas.
-
E.
Baniva
Baniva is an alternate name for the Baniwa language, an Arawakan language spoken by Indigenous communities in the northwest Amazon region of Brazil, Colombia, and Venezuela.
- 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_69d8076e64308190904fb5c93517c901 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d980bd305c8190bcf191b2d35ec8de |
completed | April 10, 2026, 10:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6cbe0bf3081909ff498ac66cb2aa6 |
completed | May 3, 2026, 4:15 a.m. |
| NEDg | Description generation | batch_69f6cd0e88e08190a07468336bb624f0 |
completed | May 3, 2026, 4:20 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f6ce2c7630819091433543dfdf8402 |
completed | May 3, 2026, 4:25 a.m. |
Created at: April 9, 2026, 8:58 p.m.