Triple
T3855297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HSBC Main Building, Hong Kong |
E89997
|
entity |
| Predicate | materialsUsed |
P1272
|
FINISHED |
| Object | steel |
—
|
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: steel | Statement: [HSBC Main Building, Hong Kong, materialsUsed, steel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: materialsUsed Context triple: [HSBC Main Building, Hong Kong, materialsUsed, steel]
-
A.
materialUsed
chosen
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
B.
featuresMaterialFrom
Indicates that one entity incorporates, contains, or is composed of material originating from another entity.
-
C.
materialProvidedFor
Indicates that one entity supplies or makes available a material for use, processing, or incorporation by another entity or purpose.
-
D.
materialInvolved
Indicates that a particular material participates in, is used by, or is otherwise involved in the referenced process, event, or relationship.
-
E.
materialDepicted
Indicates that a work or representation visually portrays or includes a particular material as part of its subject.
- 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_69aed95b3c088190a8f85d19e6070599 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeec05ec4c8190bd5e5463163712dc |
completed | March 9, 2026, 3:49 p.m. |
| PD | Predicate disambiguation | batch_69aee752c8a48190a670f73ed0bf1e61 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:19 p.m.