Triple
T1261384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jin Mao Tower |
E12508
|
entity |
| Predicate | observationDeckHeight_m |
P5396
|
FINISHED |
| Object | 340 |
—
|
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: 340 | Statement: [Jin Mao Tower, observationDeckHeight_m, 340]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: observationDeckHeight_m Context triple: [Jin Mao Tower, observationDeckHeight_m, 340]
-
A.
observationDeckHeight
chosen
Indicates the vertical distance of an observation deck above a reference level, typically the ground or sea level.
-
B.
observationDeckFloor
Indicates the specific floor or level of a building on which an observation deck is located.
-
C.
hasTowerHeight
Indicates that an entity (such as a tower or structure) has a specific height value associated with it.
-
D.
naveHeight
Indicates the vertical distance from the floor to the highest point of the nave space in a building.
-
E.
architecturalHeight
Indicates the measured vertical extent of a structure based on its architectural design, typically from the lowest significant level to the highest architecturally integral point, excluding non-architectural elements like antennas or masts.
- 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_69a4933352e08190ac617291985e76c0 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4bfc64e648190b9c4f980eb8168aa |
completed | March 1, 2026, 10:37 p.m. |
| PD | Predicate disambiguation | batch_69a4bb6eefbc81908dddd7d2ef368186 |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:50 p.m.