Triple
T30899921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robyn Crawford |
E787132
|
entity |
| Predicate | sharesTopicWith |
P76081
|
FINISHED |
| Object | Whitney Houston |
—
|
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: Whitney Houston | Statement: [Robyn Crawford, sharesTopicWith, Whitney Houston]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesTopicWith Context triple: [Robyn Crawford, sharesTopicWith, Whitney Houston]
-
A.
sharesSubjectWith
chosen
Indicates that two items are associated with or pertain to the same subject or topic.
-
B.
sharesThemeWith
Indicates that two entities are related by having the same or closely similar underlying theme or subject matter.
-
C.
sharesUniverseWith
Indicates that two entities exist within the same fictional or narrative universe, implying shared continuity, setting, or canon.
-
D.
sharesModuleWith
Indicates that two entities are associated with or participate in at least one common module.
-
E.
shareWith
Indicates that something is given, disclosed, or made accessible by one entity to another entity.
- 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_69f224bcbcb48190836df847424e4057 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fe8f74748c8190bd14a856c057f9f7 |
completed | May 9, 2026, 1:35 a.m. |
| PD | Predicate disambiguation | batch_69fe8e7ed8088190929e0df67aca4de9 |
completed | May 9, 2026, 1:31 a.m. |
Created at: April 29, 2026, 8:50 p.m.