Triple
T30954597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kate Moss |
E788639
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object |
Lila Grace Moss Hack
Lila Grace Moss Hack is a British fashion model and the daughter of supermodel Kate Moss and publisher Jefferson Hack.
|
E1938894
|
NE 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: Lila Grace Moss Hack | Statement: [Kate Moss, hasChild, Lila Grace Moss Hack]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lila Grace Moss Hack Triple: [Kate Moss, hasChild, Lila Grace Moss Hack]
Generated description
Lila Grace Moss Hack is a British fashion model and the daughter of supermodel Kate Moss and publisher Jefferson Hack.
Provenance (5 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_69f224c28c1881908c33b45d689f1724 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6934796808190b5fc783f441d44a0 |
completed | May 3, 2026, 12:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a28e483a78c819085d94bacfb2d789e |
completed | June 10, 2026, 4:13 a.m. |
| NEDg | Description generation | batch_6a28e86225188190a5aa53d9baa03bcc |
completed | June 10, 2026, 4:30 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a28e8c7896c81909d9549c47419c25f |
completed | June 10, 2026, 4:32 a.m. |
Created at: April 29, 2026, 8:53 p.m.