Triple
T27490845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emanuel Celler |
E693878
|
entity |
| Predicate | startTimeOfServiceInHouse |
P61845
|
FINISHED |
| Object | 1923 |
—
|
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: 1923 | Statement: [Emanuel Celler, startTimeOfServiceInHouse, 1923]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTimeOfServiceInHouse Context triple: [Emanuel Celler, startTimeOfServiceInHouse, 1923]
-
A.
startTimeAsHeadOfHouse
Indicates the time at which an entity begins serving as the head of a household.
-
B.
hasServiceTime
Indicates that an entity is associated with a specific duration or schedule during which a service is provided.
-
C.
servedTimeAt
Indicates the specific time period during which an entity was served or received service at a particular place or context.
-
D.
servedTimeFor
Indicates that one entity has completed or spent a specified duration of time serving a sentence, obligation, or term on behalf of another entity or for a particular case or offense.
-
E.
serviceEntryDate
chosen
Indicates the date on which a service or duty officially began or was first entered into the record.
- 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_69ef5382b9648190be0b1ef2ad5d043c |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69fcf36d2894819089b7db8e91b63c9d |
completed | May 7, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69fcf25c0a108190bfa823474098640b |
completed | May 7, 2026, 8:13 p.m. |
Created at: April 27, 2026, 1:05 p.m.