Triple
T34013122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hang Seng indices |
E872165
|
entity |
| Predicate | includesConstituentsFrom |
P112016
|
FINISHED |
| Object | H-shares |
E245429
|
NE 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: H-shares | Statement: [Hang Seng indices, includesConstituentsFrom, H-shares]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesConstituentsFrom Context triple: [Hang Seng indices, includesConstituentsFrom, H-shares]
-
A.
usesConstituentsFrom
chosen
Indicates that one entity is composed of, incorporates, or is derived from specific constituent parts provided by another entity.
-
B.
constitutedBy
Indicates that something is made up of, composed from, or formed by the specified parts or elements.
-
C.
numberOfConstituents
Indicates the total count of individual components or members that make up a larger whole or group.
-
D.
representedConstituentsFrom
Indicates that an entity served as a representative or proxy for certain constituents originating from another entity or source.
-
E.
containsConstituency
Indicates that one entity includes or encompasses another entity as part of its constituency or membership.
- F. None of above.
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_69f349a08848819084b348d64c1879c3 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3692f19f948190a1d1946eb69ed43b |
completed | June 20, 2026, 1:17 p.m. |
| PD | Predicate disambiguation | batch_6a0379f963908190846d232f386fd98f |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:51 a.m.