Triple
T30180639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | territory of Ceylon |
E767189
|
entity |
| Predicate | usedAsTerritoryUntil |
P81220
|
FINISHED |
| Object | Republic of Sri Lanka (1972) |
—
|
NE NERFINISHED |
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: Republic of Sri Lanka (1972) | Statement: [territory of Ceylon, usedAsTerritoryUntil, Republic of Sri Lanka (1972)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsTerritoryUntil Context triple: [territory of Ceylon, usedAsTerritoryUntil, Republic of Sri Lanka (1972)]
-
A.
usedAsTerritoryFrom
Indicates that an entity served as a territory for another entity starting from a specified point in time.
-
B.
usedAsPrimarySettlementUntil
Indicates that an entity served as the main or principal settlement for another entity up to a specified point in time.
-
C.
territoryAtTime
chosen
Indicates that a specified territory is associated with or held by an entity during a particular time or time interval.
-
D.
wasPopulatedPlaceUntil
Indicates that a location functioned as a populated place up to a specified point in time, after which it no longer held that status.
-
E.
usedAsTownNameUntil
Indicates that an entity served as the official or common name of a town up to a specified point in time.
- 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_69f2247ba20c81909d34f2bfed706e1e |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd0b92f42881908cd77e3f058adcc2 |
completed | May 7, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fd0a3d68d4819094d92040f7c48d7c |
completed | May 7, 2026, 9:55 p.m. |
Created at: April 29, 2026, 7:26 p.m.