Triple
T1671546
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanghai Tower |
E36135
|
entity |
| Predicate | rankAmongTallestBuildings |
P31595
|
FINISHED |
| Object | one of the tallest buildings in the world |
—
|
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: one of the tallest buildings in the world | Statement: [Shanghai Tower, rankAmongTallestBuildings, one of the tallest buildings in the world]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankAmongTallestBuildings Context triple: [Shanghai Tower, rankAmongTallestBuildings, one of the tallest buildings in the world]
-
A.
rankInCityByHeight
Indicates the relative ordering of entities within a specific city based on their height, such as which is tallest, second tallest, and so on.
-
B.
tallestBuildingIn
Indicates that one entity is the tallest building located within the area or region specified by the other entity.
-
C.
rankInShanghaiByHeightCurrent
Indicates the position an entity currently holds in a ranking of heights within Shanghai, ordered from tallest to shortest.
-
D.
towerName
Indicates the specific name assigned to a tower in the relationship.
-
E.
buildingHeightContext
Indicates the contextual or situational factors under which a building’s height is defined, measured, or interpreted.
- 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_69a8861286808190939afff3ce8ee31e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69ab272a653481908f48aa1eed5de8a4 |
completed | March 6, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_69aa61b2f6288190b2348ef7d7e4672d |
completed | March 6, 2026, 5:10 a.m. |
| PDg | Predicate description generation | batch_69ab271be3f4819091adcd745dec8159 |
completed | March 6, 2026, 7:12 p.m. |
Created at: March 4, 2026, 7:29 p.m.