Triple
T6700486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hugo Award for Best Novella |
E152865
|
entity |
| Predicate | wordCountRange |
P7605
|
FINISHED |
| Object | 17500–40000 words |
—
|
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: 17500–40000 words | Statement: [Hugo Award for Best Novella, wordCountRange, 17500–40000 words]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wordCountRange Context triple: [Hugo Award for Best Novella, wordCountRange, 17500–40000 words]
-
A.
wordCount
chosen
Indicates the total number of words contained in a given text or linguistic unit.
-
B.
wordLength
Indicates that there is a relationship specifying the number of characters (length) in a given word.
-
C.
sentenceLength
Indicates the length or number of units (such as characters, words, or tokens) that a given sentence contains.
-
D.
hasApproximateNumberOfLetters
Indicates that an entity is associated with a number that roughly, but not exactly, corresponds to the count of letters it contains.
-
E.
includesNumberingRange
Indicates that one entity contains or covers a specified contiguous range of numbers associated with another entity.
- 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_69c68807adbc8190b8632df42b39eda0 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d16897e48190b43eda2206b14d6a |
completed | March 27, 2026, 6:50 p.m. |
| PD | Predicate disambiguation | batch_69c6d089c7488190a00853fb12f53b2a |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:05 p.m.