Triple
T5008035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hi5 |
E112544
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Ramu Yalamanchi |
E488255
|
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: Ramu Yalamanchi | Statement: [Hi5, foundedBy, Ramu Yalamanchi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ramu Yalamanchi Context triple: [Hi5, foundedBy, Ramu Yalamanchi]
-
A.
Ramu Yalamanchi
chosen
Ramu Yalamanchi is an entrepreneur best known as the founder of the early social networking site hi5.
-
B.
Janardhan Rao
Janardhan Rao was a son of the prominent Maratha Peshwa Baji Rao I, belonging to the influential Peshwa family of the Maratha Empire.
-
C.
Manohar Raju
Manohar Raju is an American attorney and criminal justice reform advocate who serves as the elected Public Defender of San Francisco.
-
D.
D. Ramanaidu
D. Ramanaidu was a prolific Indian film producer and founder of Suresh Productions, renowned for holding a Guinness World Record for producing the most films.
-
E.
Koratala Siva
Koratala Siva is an Indian film director and screenwriter known for his socially conscious and commercially successful Telugu-language films.
- 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_69bd4433d0b08190877e83959ef40d81 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd72eb05f881908d7dc3d7cd07b2ae |
completed | March 20, 2026, 4:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bea473a1708190aaf4a021fec472c6 |
completed | March 21, 2026, 2 p.m. |
Created at: March 20, 2026, 1:35 p.m.