Triple
T28605456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hilly Brown |
E724032
|
entity |
| Predicate | hasPsychicLinkWith |
P66148
|
FINISHED |
| Object | alien influence in Haven |
—
|
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: alien influence in Haven | Statement: [Hilly Brown, hasPsychicLinkWith, alien influence in Haven]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPsychicLinkWith Context triple: [Hilly Brown, hasPsychicLinkWith, alien influence in Haven]
-
A.
sharesTelepathicBondWith
chosen
Indicates a mutual telepathic connection through which two entities can directly share thoughts, feelings, or information.
-
B.
hasChildWithPsychicAbility
Indicates that an entity has at least one child who possesses a psychic or supernatural mental ability.
-
C.
hasSupernaturalConnectionWith
Indicates a special, non-natural bond or interaction exists between two entities that involves supernatural forces, powers, or phenomena.
-
D.
hasMagicCompanion
Indicates that an entity is accompanied by or associated with another entity that serves as its magical companion.
-
E.
hasMysteriousConnectionWith
Indicates a vague or unexplained relationship or association exists between two entities, whose nature or cause is not clearly understood.
- 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_69f01d816d7c8190a1fe27e3434041dc |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f652a492108190b885b955ce147d3c |
completed | May 2, 2026, 7:38 p.m. |
| PD | Predicate disambiguation | batch_69f651aad92c8190b874b3b5f9f64434 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 4:27 a.m.