Triple
T15058392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gampaha District |
E379556
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Mahara
Mahara is a suburban town in Sri Lanka’s Western Province, situated within the Gampaha District and known for its residential communities and local institutions.
|
E1135858
|
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: Mahara | Statement: [Gampaha District, contains, Mahara]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mahara Context triple: [Gampaha District, contains, Mahara]
-
A.
Sakai
Sakai is a major Japanese city in Osaka Prefecture known historically as a prosperous port and merchant center and today as an important industrial and cultural hub.
-
B.
Mabang
Mabang is an alternative name for the Maba language, a Nilo-Saharan language spoken primarily in Chad.
-
C.
Alura
Alura is Supergirl’s Kryptonian mother, often depicted as a prominent scientist and leader on Krypton in DC Comics lore.
-
D.
Sakai Port
Sakai Port is a historic Japanese harbor city area in Osaka Prefecture that has long served as a key commercial and maritime gateway.
-
E.
Tantripala
Tantripala is an alternate name for Sahadeva, one of the five Pandava princes in the Indian epic Mahabharata.
- 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: Mahara Triple: [Gampaha District, contains, Mahara]
Generated description
Mahara is a suburban town in Sri Lanka’s Western Province, situated within the Gampaha District and known for its residential communities and local institutions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mahara Target entity description: Mahara is a suburban town in Sri Lanka’s Western Province, situated within the Gampaha District and known for its residential communities and local institutions.
-
A.
Sakai
Sakai is a major Japanese city in Osaka Prefecture known historically as a prosperous port and merchant center and today as an important industrial and cultural hub.
-
B.
Mabang
Mabang is an alternative name for the Maba language, a Nilo-Saharan language spoken primarily in Chad.
-
C.
Alura
Alura is Supergirl’s Kryptonian mother, often depicted as a prominent scientist and leader on Krypton in DC Comics lore.
-
D.
Sakai Port
Sakai Port is a historic Japanese harbor city area in Osaka Prefecture that has long served as a key commercial and maritime gateway.
-
E.
Tantripala
Tantripala is an alternate name for Sahadeva, one of the five Pandava princes in the Indian epic Mahabharata.
- 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_69d85cd64d108190853797a95c11cc45 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dedee50afc8190bf7b0f4bbe8c60a3 |
completed | April 15, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fea5c2fcec8190800d1bda82c7352e |
completed | May 9, 2026, 3:10 a.m. |
| NEDg | Description generation | batch_69fea9c0ad748190989920efe418001c |
completed | May 9, 2026, 3:28 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69feaa2fbafc8190b592d89b07b49765 |
completed | May 9, 2026, 3:29 a.m. |
Created at: April 10, 2026, 3:01 a.m.