Triple
T19162108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shunem |
E469080
|
entity |
| Predicate | alternativeName |
P39
|
FINISHED |
| Object | Sunem |
—
|
NE NERFINISHED |
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: Sunem | Statement: [Shunem, alternativeName, Sunem]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sunem Context triple: [Shunem, alternativeName, Sunem]
-
A.
Sunem
chosen
Sunem is an ancient town in the Jezreel Valley region of Israel, traditionally identified with the biblical village of Shunem mentioned in the Hebrew Bible.
-
B.
Nanakramguda
Nanakramguda is a prominent IT and financial district in Hyderabad, India, known for housing major technology parks, corporate offices, and the city’s financial services hub.
-
C.
Bolarum
Bolarum is a suburban residential and cantonment area in the northern part of Hyderabad, India, known for its military establishments and colonial-era buildings.
-
D.
Srikalahasti
Srikalahasti is a temple town in Andhra Pradesh, India, renowned for its ancient Shiva temple and strong religious significance.
-
E.
Vandiyur
Vandiyur is a locality in Madurai, Tamil Nadu, known for its historic temple tank and religious significance.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd084ff48190ac0f8c46ee722629 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5eebe03ac8190bbe0b34ebf0d90c6 |
completed | April 20, 2026, 9:15 a.m. |
Created at: April 10, 2026, 12:06 p.m.