Triple
T120572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boston Marathon |
E2435
|
entity |
| Predicate | fieldSize |
P7759
|
FINISHED |
| Object | tens of thousands of participants |
—
|
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 of participants | Statement: [Boston Marathon, fieldSize, tens of thousands of participants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fieldSize Context triple: [Boston Marathon, fieldSize, tens of thousands of participants]
-
A.
bodySize
Indicates the relative physical magnitude or scale of an entity’s body, such as how large or small it is.
-
B.
islandSize
Indicates the size or area measurement associated with a particular island.
-
C.
length
Indicates a measurement relationship where a value specifies how long something is from one end to the other.
-
D.
fieldType
Indicates the classification or category that defines the nature or kind of a given field within a structure or context.
-
E.
fieldPattern
Indicates a recurring or structured arrangement or configuration present within a field or area.
- F. None of above. chosen
Provenance (4 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_69a2506c5428819085c28a8884790e29 |
completed | Feb. 28, 2026, 2:18 a.m. |
| NER | Named-entity recognition | batch_69a258fd278481908ad4498e03f38e2f |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a25647fe6081908cb0405266d35ff5 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a258fbd18881908c9d40f7a2480945 |
completed | Feb. 28, 2026, 2:54 a.m. |
Created at: Feb. 28, 2026, 2:24 a.m.