Triple
T33651500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hang Seng Bank |
E862110
|
entity |
| Predicate | roleInProduct |
P87777
|
FINISHED |
| Object | compiler of Hang Seng Index |
—
|
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: compiler of Hang Seng Index | Statement: [Hang Seng Bank, roleInProduct, compiler of Hang Seng Index]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInProduct Context triple: [Hang Seng Bank, roleInProduct, compiler of Hang Seng Index]
-
A.
roleInProductLine
chosen
Indicates the specific functional or organizational role an entity holds within a particular product line.
-
B.
productRole
Indicates the functional role or purpose that a product has within a broader system, context, or usage scenario.
-
C.
roleInSpecification
Indicates that an entity participates in a specification with a particular role or function within that specification.
-
D.
roleInIntegration
Indicates the specific function or responsibility an entity has within a combined or coordinated system, process, or integration.
-
E.
roleInDesignOf
Indicates that an entity participated in or held a specific function within the process of designing another 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_69f349840ba881908e3bfce536aeb92b |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a009273634c8190b5b9c87053b56760 |
completed | May 10, 2026, 2:13 p.m. |
| PD | Predicate disambiguation | batch_6a0092171230819096e4274dd97e0410 |
completed | May 10, 2026, 2:11 p.m. |
Created at: May 1, 2026, 1:42 a.m.