Triple
T4625771
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saruman |
E101092
|
entity |
| Predicate | opposes |
P437
|
FINISHED |
| Object | Rohan |
E261161
|
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: Rohan | Statement: [Saruman, opposes, Rohan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rohan Context triple: [Saruman, opposes, Rohan]
-
A.
Rohan
chosen
Rohan is a prominent kingdom of horse-lords in J.R.R. Tolkien’s Middle-earth, renowned for its vast grasslands and skilled cavalry.
-
B.
Ravi
Ravi is one of the major rivers of northern India and Pakistan, flowing through the Punjab region and serving as an important tributary of the Indus River system.
-
C.
Raj
Raj is the given name of Raj Reddy, a pioneering computer scientist known for his foundational work in artificial intelligence and robotics.
-
D.
Aryaman
Aryaman is a Vedic Hindu deity associated with friendship, hospitality, and social bonds, often linked with the Adityas and solar aspects.
-
E.
Nakula
Nakula is a heroic prince in the Indian epic Mahabharata, renowned as one of the five Pandava brothers and celebrated for his exceptional skill in swordsmanship and horse-keeping.
- 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_69bd43d0497c8190ac23c65c5804846a |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5a08ef488190af46418229309b0f |
completed | March 20, 2026, 2:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdfaab30508190881828adab92ba22 |
completed | March 21, 2026, 1:55 a.m. |
Created at: March 20, 2026, 1:13 p.m.