Triple
T7924410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tikkana Somayaji |
E184023
|
entity |
| Predicate | sharesGroupWith |
P32181
|
FINISHED |
| Object | Errana |
E180167
|
NE FINISHED |
How this triple was built (2 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: Errana | Statement: [Tikkana Somayaji, sharesGroupWith, Errana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Errana Context triple: [Tikkana Somayaji, sharesGroupWith, Errana]
-
A.
Errana
chosen
Errana is a medieval Telugu poet known for collaborating on and continuing the composition of the Telugu Mahabharata.
-
B.
Anredera
Anredera is a genus of flowering vines known for their twining growth habit and fleshy leaves, some species of which are cultivated as ornamentals or edible plants.
-
C.
Teraina
Teraina is a remote, low-lying coral atoll in the central Pacific Ocean that forms part of the Republic of Kiribati.
-
D.
Nolana
Nolana is a genus of flowering plants native mainly to coastal regions of South America, known for their showy, often blue, funnel-shaped blossoms.
-
E.
Arida
Arida is a city in Japan known for its agricultural production, particularly high-quality citrus fruits, within Wakayama Prefecture.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca828fe7bc819090f52c88dcd72183 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3aac02bc8190b13fc354a4fa91d3 |
completed | March 31, 2026, 3:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc63aae4dc81908cbe4a89d6bd359c |
completed | April 1, 2026, 12:15 a.m. |
Created at: March 30, 2026, 5:06 p.m.