Triple
T30088103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hylas |
E764652
|
entity |
| Predicate | abductionCause |
P168439
|
FINISHED |
| Object | nymphs fell in love with his beauty |
—
|
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: nymphs fell in love with his beauty | Statement: [Hylas, abductionCause, nymphs fell in love with his beauty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: abductionCause Context triple: [Hylas, abductionCause, nymphs fell in love with his beauty]
-
A.
abductionContext
Indicates a contextual relationship in which an abduction event occurs, specifying the surrounding circumstances, conditions, or setting of that abduction.
-
B.
usedAbductions
Indicates that one entity carried out or relied on abductions (kidnappings) as a method or tactic in relation to another entity or context.
-
C.
abductionMotif
Indicates a relationship where an event, narrative, or depiction involves the motif of one entity abducting or forcibly carrying off another.
-
D.
abductedBy
Indicates that an entity has been forcibly taken or carried away by another entity against their will.
-
E.
canAbduct
Indicates that one entity has the ability or potential to forcibly take away or kidnap another entity.
- 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_69f22473c0fc8190a926a8051b3b378b |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67d6de8a081909e426dcdf9fe0536 |
completed | May 2, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
| PDg | Predicate description generation | batch_69f6749f205c81909d1aacf462912eee |
completed | May 2, 2026, 10:03 p.m. |
Created at: April 29, 2026, 7:04 p.m.