Triple
T19081193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miracle of the Sun |
E467035
|
entity |
| Predicate | hasWitnessCountEstimate |
P109137
|
FINISHED |
| Object | tens of thousands |
—
|
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: tens of thousands | Statement: [Miracle of the Sun, hasWitnessCountEstimate, tens of thousands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWitnessCountEstimate Context triple: [Miracle of the Sun, hasWitnessCountEstimate, tens of thousands]
-
A.
witnessCount
chosen
Indicates the number of distinct witnesses associated with a particular event, action, or relationship.
-
B.
hasPrimaryWitness
Indicates that an entity is the main or principal witness associated with another entity or event.
-
C.
hasProofCount
Indicates the number of proofs or supporting evidential items associated with a given entity or claim.
-
D.
hasApproximateNumberOfNativeSignatories
Indicates that an entity is associated with an estimated or approximate count of native signatories involved with it.
-
E.
hasApproximateNumberOfAttestedWords
Indicates that an entity is associated with an estimated or approximate count of words that are documented or attested for it.
- 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_69d8dd04f4488190b1121cc53ef2bfd6 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e2e8f8148190942cca6dd3e30caf |
completed | April 20, 2026, 8:25 a.m. |
| PD | Predicate disambiguation | batch_69e4b9a604308190a3235184f9f2c056 |
completed | April 19, 2026, 11:16 a.m. |
Created at: April 10, 2026, 12:04 p.m.