Triple
T15782230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terry Linden |
E382645
|
entity |
| Predicate | relationshipTypeWith Hank Evans |
P119989
|
FINISHED |
| Object | friend of spouse's colleague |
—
|
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: friend of spouse's colleague | Statement: [Terry Linden, relationshipTypeWith Hank Evans, friend of spouse's colleague]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWith Hank Evans Context triple: [Terry Linden, relationshipTypeWith Hank Evans, friend of spouse's colleague]
-
A.
relationshipToEvanHansen
Indicates the type or nature of a person's relationship or connection to Evan Hansen.
-
B.
relationshipToEveHarrington
Indicates the nature or role of one entity’s connection or association to Eve Harrington.
-
C.
relationshipToHannah
Indicates the specific type of relationship or connection that an entity has to Hannah.
-
D.
relationshipTypeWith Eugene Gant
Indicates the specific nature or category of relationship that an entity has with Eugene Gant.
-
E.
relationshipToHenry
Indicates the specific type of relationship or connection that an entity has to Henry.
- F. None of above. chosen
Provenance (4 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_69d86da09a10819082fe9797b23e4664 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e05400716881909bc43212c8ea54d5 |
completed | April 16, 2026, 3:14 a.m. |
| PD | Predicate disambiguation | batch_69e00537bd1c81908d6e832792fd934f |
completed | April 15, 2026, 9:37 p.m. |
| PDg | Predicate description generation | batch_69e006b17f7881908b8c7a37f0af4581 |
completed | April 15, 2026, 9:44 p.m. |
Created at: April 10, 2026, 4:48 a.m.