Triple
T35295395
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anne Sullivan |
E1019350
|
entity |
| Predicate | lifelongCompanion |
P22642
|
FINISHED |
| Object | Helen Keller |
—
|
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: Helen Keller | Statement: [Anne Sullivan, lifelongCompanion, Helen Keller]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lifelongCompanion Context triple: [Anne Sullivan, lifelongCompanion, Helen Keller]
-
A.
companionOf
chosen
Indicates that one entity serves as a companion or partner to another, typically accompanying or being closely associated with them.
-
B.
longTermPartner
Indicates a romantic relationship in which two people are committed partners over an extended period of time without necessarily being married.
-
C.
competesForAffectionWith
Indicates a relationship where two or more entities vie against each other to gain the affection or emotional favor of the same target entity.
-
D.
successorCompanion
Indicates that one entity serves as the subsequent or replacement companion to another entity in a sequence or timeline.
-
E.
associatedWithAnimal
Indicates a relationship where an entity has a connection, link, or relevance to an animal.
- 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_69f76de7eedc8190a3bdc64ebbc05b42 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7901ccb748190bb39013b50761c01 |
completed | May 3, 2026, 6:12 p.m. |
| PD | Predicate disambiguation | batch_69f78e2f52e08190a77661223a96c601 |
completed | May 3, 2026, 6:04 p.m. |
Created at: May 3, 2026, 4:03 p.m.