Triple
T9790661
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Santhome |
E237596
|
entity |
| Predicate | hasRoad |
P959
|
FINISHED |
| Object | Kamarajar Salai |
E46426
|
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: Kamarajar Salai | Statement: [Santhome, hasRoad, Kamarajar Salai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kamarajar Salai Context triple: [Santhome, hasRoad, Kamarajar Salai]
-
A.
Kamarajar Salai
chosen
Kamarajar Salai is a prominent seaside arterial road in Chennai, India, running along the Marina Beach and hosting several important educational and governmental landmarks.
-
B.
Palamoor
Palamoor is the historical name of Mahbubnagar, a town and district headquarters in the Indian state of Telangana.
-
C.
Nandighosa
Nandighosa is the grand, elaborately decorated main chariot used to carry Lord Jagannath during the annual Rath Yatra festival in Puri, India.
-
D.
Salasar Balaji
Salasar Balaji is a renowned Hindu pilgrimage site in Rajasthan, India, famous for its temple dedicated to Lord Hanuman.
-
E.
Attara Kacheri
Attara Kacheri is a historic red-brick, neoclassical building in Bengaluru that houses the High Court of Karnataka.
- 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_69ca84dc04488190b9c91193976c0960 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda215b3108190a897552e1dc91cc4 |
completed | April 1, 2026, 10:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1c43141cc81908c45a3f5d5103564 |
completed | April 5, 2026, 2:08 a.m. |
Created at: March 30, 2026, 8:28 p.m.