Triple
T19495637
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanema language |
E487761
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object |
Tanima
Tanima is an alternate name for the Tanema language, an endangered Oceanic language once spoken in the Solomon Islands.
|
E1379162
|
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: Tanima | Statement: [Tanema language, hasAlternativeName, Tanima]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tanima Context triple: [Tanema language, hasAlternativeName, Tanima]
-
A.
Almas
Almas is a cryptid from Central Asian folklore, often described as a relict hominid or wild, ape-like humanoid similar to Bigfoot.
-
B.
Tohana
Tohana is a town and municipal council in the Fatehabad district of the Indian state of Haryana, known as an agricultural and trading center in the region.
-
C.
Yozora
Yozora is a prominent music producer recognized for shaping the sound and energy of New York’s drill scene.
-
D.
Nigō
Nigō is the Japanese fashion designer, DJ, and entrepreneur best known as the founder of the streetwear brand A Bathing Ape (BAPE) and co-founder of Billionaire Boys Club.
-
E.
Nakoruru
Nakoruru is a popular Samurai Shodown character known as a nature-loving Ainu shrine maiden who fights alongside her hawk and wolf companions.
- 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: Tanima Triple: [Tanema language, hasAlternativeName, Tanima]
Generated description
Tanima is an alternate name for the Tanema language, an endangered Oceanic language once spoken in the Solomon Islands.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tanima Target entity description: Tanima is an alternate name for the Tanema language, an endangered Oceanic language once spoken in the Solomon Islands.
-
A.
Almas
Almas is a cryptid from Central Asian folklore, often described as a relict hominid or wild, ape-like humanoid similar to Bigfoot.
-
B.
Tohana
Tohana is a town and municipal council in the Fatehabad district of the Indian state of Haryana, known as an agricultural and trading center in the region.
-
C.
Yozora
Yozora is a prominent music producer recognized for shaping the sound and energy of New York’s drill scene.
-
D.
Nigō
Nigō is the Japanese fashion designer, DJ, and entrepreneur best known as the founder of the streetwear brand A Bathing Ape (BAPE) and co-founder of Billionaire Boys Club.
-
E.
Nakoruru
Nakoruru is a popular Samurai Shodown character known as a nature-loving Ainu shrine maiden who fights alongside her hawk and wolf companions.
- 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_69d8e8d9d1c88190b01cd78b8be49384 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6349182ec81908dd301f802530eec |
completed | April 20, 2026, 2:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0740622cd88190965b3eb6e644cb6f |
completed | May 15, 2026, 3:48 p.m. |
| NEDg | Description generation | batch_6a0744467d6c819082aa0933a0b9ba65 |
completed | May 15, 2026, 4:05 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0744ddbc3c8190b21d691a84e3ef92 |
completed | May 15, 2026, 4:07 p.m. |
Created at: April 10, 2026, 1:40 p.m.