Triple
T37170406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | church in Philemon’s house |
E920892
|
entity |
| Predicate | metInHouseOf |
P183775
|
FINISHED |
| Object | Philemon |
—
|
NE NERFINISHED |
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: Philemon | Statement: [church in Philemon’s house, metInHouseOf, Philemon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: metInHouseOf Context triple: [church in Philemon’s house, metInHouseOf, Philemon]
-
A.
metThrough
Indicates that two entities became acquainted or connected as a result of an intermediary person, event, platform, or context through which they first met.
-
B.
houseChamber
Indicates that one entity is a legislative chamber that is part of, or belongs to, a particular house (e.g., upper or lower house) within a legislative body.
-
C.
intendedToHouse
Indicates that one entity is designed or meant to serve as a dwelling or accommodation space for another entity.
-
D.
houseIsLocationOf
chosen
Indicates that a house serves as the place where a particular entity, event, or activity is located or occurs.
-
E.
house1
Indicates that something is identified or classified as a house or dwelling.
- 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_69f76ea16f288190b445aa1604d996f4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb55de3b9c8190a7656aeab3c3ffbc |
completed | May 6, 2026, 2:53 p.m. |
| PD | Predicate disambiguation | batch_69fb35bc92e08190bff447624e2df791 |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:15 p.m.