Triple
T37636413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maligawa Tusker |
E936498
|
entity |
| Predicate | locationDuringFestival |
P89358
|
FINISHED |
| Object | streets of Kandy |
—
|
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: streets of Kandy | Statement: [Maligawa Tusker, locationDuringFestival, streets of Kandy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationDuringFestival Context triple: [Maligawa Tusker, locationDuringFestival, streets of Kandy]
-
A.
positionInFestival
Indicates the specific role, slot, or placement an entity holds within the structure or schedule of a festival.
-
B.
locatedInFestival
chosen
Indicates that something exists or takes place within the spatial or organizational boundaries of a specific festival.
-
C.
locatedInFestivalCity
Indicates that an entity is situated within or belongs to a city that is designated as a festival city.
-
D.
festivalPresence
Indicates that an entity is present at, participates in, or is associated with a particular festival event.
-
E.
festivalArea
Indicates that a location or space is designated as the area where a festival takes place or is held.
- 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_69f76ed31d8881908405da6c6d2f0463 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1553e08190bb7424c448cb1f33 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:18 p.m.