Triple

T34393990
Position Surface form Disambiguated ID Type / Status
Subject Mapletree Investments E882779 entity
Predicate followsStrategy P198067 FINISHED
Object capital recycling 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: capital recycling | Statement: [Mapletree Investments, followsStrategy, capital recycling]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: followsStrategy
Context triple: [Mapletree Investments, followsStrategy, capital recycling]
  • A. followsReleaseStrategyOf
    Indicates that one entity adopts or adheres to the same release strategy or release management approach as another entity.
  • B. followsStructure
    Indicates that one entity adheres to, conforms with, or is organized according to the structural pattern defined by another entity.
  • C. followsBetween
    Indicates that one entity comes after or succeeds another entity within a specified context or sequence.
  • D. followsPass
    Indicates that one entity moves behind or in the path of another entity who has just passed, maintaining a trailing or subsequent position.
  • E. followsPlanType
    Indicates that one entity adheres to, or is carried out according to, a specified type of plan.
  • F. None of above. chosen

Provenance (4 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_69f349c1304081909331872829e38106 completed April 30, 2026, 12:23 p.m.
NER Named-entity recognition batch_69fec5c503808190bde0b1829ea43071 completed May 9, 2026, 5:27 a.m.
PD Predicate disambiguation batch_69fec535dd6c8190a6ab85201f5a04a9 completed May 9, 2026, 5:25 a.m.
PDg Predicate description generation batch_69fec5c3f8248190b835a8e4eba470c4 completed May 9, 2026, 5:27 a.m.
Created at: May 1, 2026, 1:59 a.m.