Triple
T19980663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sonnet 55 |
E493807
|
entity |
| Predicate | totalLines |
P4876
|
FINISHED |
| Object | 14 |
—
|
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: 14 | Statement: [Sonnet 55, totalLines, 14]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: totalLines Context triple: [Sonnet 55, totalLines, 14]
-
A.
fastLinesUsedBy
Indicates that certain fast transportation or communication lines are utilized by a particular entity.
-
B.
hasNumberOfLines
chosen
Indicates the relationship that specifies how many lines are associated with a given entity.
-
C.
inscriptionNumberOfLines
Indicates the number of distinct lines that appear in an inscription.
-
D.
hasDeepLevelLines
Indicates that one entity possesses or exhibits lines that extend to or occur at a deep level within a given structure or context.
-
E.
totalSystemLength
Indicates the complete measured length of an entire system, aggregating all its relevant components or segments.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65d12d968819081e315ec4585cd9f |
completed | April 20, 2026, 5:06 p.m. |
| PD | Predicate disambiguation | batch_69e537fae79c81909eae39500766d0b6 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 11, 2026, 3:28 p.m.