Triple
T26581645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ed Markey |
E667094
|
entity |
| Predicate | servedInUSHouseFrom |
P80020
|
FINISHED |
| Object | 1976 |
—
|
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: 1976 | Statement: [Ed Markey, servedInUSHouseFrom, 1976]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedInUSHouseFrom Context triple: [Ed Markey, servedInUSHouseFrom, 1976]
-
A.
servedInCongress
Indicates that an individual held an official legislative position as a member of a national congress during some period of time.
-
B.
wasARepresentativeFor
Indicates that one entity served as an official representative or delegate acting on behalf of another entity.
-
C.
representedInCongressSince
Indicates that an entity has served as a representative in a legislative congress continuously since a specified date or time.
-
D.
representedInCongressBy
Indicates that one entity serves as the official congressional representative (e.g., legislator) for another entity (such as a person, group, or geographic area).
-
E.
representedInHouseOfRepresentatives
chosen
Indicates that an entity serves as a representative or has representation within a specific House of Representatives.
- 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_69ee9cfb7e548190b60a9031182f5a7e |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f78c61ed4c8190ad84c918fa9af55a |
completed | May 3, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69f78b8cb3a881909ebaac1b503988c2 |
completed | May 3, 2026, 5:53 p.m. |
Created at: April 27, 2026, 2:03 a.m.