Triple
T17301918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pete |
E420058
|
entity |
| Predicate | hasLivingSituation |
P29563
|
FINISHED |
| Object | lives with a dragon companion |
—
|
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: lives with a dragon companion | Statement: [Pete, hasLivingSituation, lives with a dragon companion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLivingSituation Context triple: [Pete, hasLivingSituation, lives with a dragon companion]
-
A.
hasHousingArrangement
Indicates that an entity has a specific type or status of housing or living arrangement in relation to another entity or context.
-
B.
residenceStatus
Indicates the type or condition of an entity’s living arrangement or place of residence in relation to a specified location.
-
C.
hasHousingAccess
Indicates that an entity has the ability, right, or opportunity to obtain or use suitable housing.
-
D.
livedWith
chosen
Indicates that two entities shared the same residence or household for a period of time.
-
E.
hasCanonicalResidence
Indicates that an entity has an officially recognized primary place of residence or domicile.
- 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_69d886db32608190a61e18862c5a8af6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e438fae8848190a06c5866e606baac |
completed | April 19, 2026, 2:07 a.m. |
| PD | Predicate disambiguation | batch_69e3b0118ad08190b119cd219c68ba67 |
completed | April 18, 2026, 4:23 p.m. |
Created at: April 10, 2026, 5:41 a.m.