Triple
T19595280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Lanka |
E470332
|
entity |
| Predicate | hasKeyDuel |
P83211
|
FINISHED |
| Object | Rama versus Ravana |
—
|
LITERAL 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: Rama versus Ravana | Statement: [Battle of Lanka, hasKeyDuel, Rama versus Ravana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKeyDuel Context triple: [Battle of Lanka, hasKeyDuel, Rama versus Ravana]
-
A.
hasKeyBattle
Indicates that an entity is associated with a major or decisive battle that is central to its history, role, or significance.
-
B.
hasKeyRitual
Indicates that an entity is associated with or performs a primary or central ritual that is fundamental to its role, function, or identity.
-
C.
hasKeyDua
Indicates that one entity possesses or is associated with a specific secondary or backup key related to another entity.
-
D.
typeOfDuel
chosen
Indicates the specific kind or category of duel that characterizes a given dueling event or relationship between opponents.
-
E.
duelArrangedBy
Indicates that a duel between two parties has been set up, initiated, or formally organized by a specific agent or entity.
- F. None of above.
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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640793cd88190b9b84491bfb2493f |
completed | April 20, 2026, 3:04 p.m. |
| PD | Predicate disambiguation | batch_69e514e166dc8190a0f147e0b4c8bbe7 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:43 p.m.