Triple
T35012039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | High Elves |
E1009958
|
entity |
| Predicate | averageHeightComparedToHumans |
P90499
|
FINISHED |
| Object | taller |
—
|
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: taller | Statement: [High Elves, averageHeightComparedToHumans, taller]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: averageHeightComparedToHumans Context triple: [High Elves, averageHeightComparedToHumans, taller]
-
A.
averageHeight
Indicates that the relationship specifies the mean height value calculated from a set of entities or measurements.
-
B.
averageHeightRange
Indicates the typical minimum and maximum height values that characterize the usual height span associated with an entity or group.
-
C.
heightInUniverse
Indicates the vertical position or elevation of an entity within a specified universe or spatial reference frame.
-
D.
heightDescription
chosen
Indicates how tall an entity is, typically expressed in descriptive or qualitative terms rather than a precise measurement.
-
E.
estimatedHeadHeightInMeters
Indicates the estimated vertical height of a person's head, measured in meters.
- 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_69f76dcc3ac8819096a3ed52f5fa2523 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 3, 2026, 4:01 p.m.