Triple
T567328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geneva Round (1947) |
E13583
|
entity |
| Predicate | hasStartYear |
P10338
|
FINISHED |
| Object | 1947 |
—
|
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: 1947 | Statement: [Geneva Round (1947), hasStartYear, 1947]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStartYear Context triple: [Geneva Round (1947), hasStartYear, 1947]
-
A.
beganInYear
chosen
Indicates that an event, process, or state started in a specific calendar year.
-
B.
approximateStartYear
Indicates that the associated year value represents an estimated or imprecise starting year for an event, state, or relationship rather than an exact one.
-
C.
settingStartYear
Indicates the year in which a particular setting, configuration, or condition first becomes effective or begins to apply.
-
D.
originYear
Indicates the year in which something first originated, was created, or began.
-
E.
productionStartYear
Indicates the year in which the production of an item, work, or entity first began.
- 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_69a4933edcf08190b35ecfd6014caee6 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49b02da148190b6a9bad3a22d8ec5 |
completed | March 1, 2026, 8:01 p.m. |
| PD | Predicate disambiguation | batch_69a494c183b081909304944aa3d0fe8f |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.