Triple
T36619206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salesforce Tower |
E903685
|
entity |
| Predicate | rankingInStateByHeight |
P191125
|
FINISHED |
| Object | tallest building in Indiana |
—
|
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: tallest building in Indiana | Statement: [Salesforce Tower, rankingInStateByHeight, tallest building in Indiana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankingInStateByHeight Context triple: [Salesforce Tower, rankingInStateByHeight, tallest building in Indiana]
-
A.
stateHighPointRank
Indicates the relative ranking position of a location as the highest point within a given state or comparable region.
-
B.
rankAmongTallestInUS
Indicates that the entity is among the tallest of its kind within the United States.
-
C.
rankingInCountryByHeight
Indicates the position an entity holds in an ordered list of entities within a specific country, when sorted by their height.
-
D.
regionRankByHeight
Indicates the relative ordering of regions based on their height or elevation.
-
E.
countryRankByHeight
Indicates the relative position of a country when countries are ordered by the height of something (e.g., average elevation, tallest point, or average citizen height).
- 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_69f76e6960e4819092047756ceb9a17e |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcda3699948190adb57625bae08091 |
completed | May 7, 2026, 6:30 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fd16d08190b0aca6e19a632e99 |
completed | May 7, 2026, 6:25 p.m. |
| PDg | Predicate description generation | batch_69fcda35dc048190a3c90e15230900e0 |
completed | May 7, 2026, 6:30 p.m. |
Created at: May 3, 2026, 4:11 p.m.