Triple
T36428601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hulton family |
E897376
|
entity |
| Predicate | hasLongstandingPresenceIn |
P175215
|
FINISHED |
| Object | Lancashire |
—
|
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: Lancashire | Statement: [Hulton family, hasLongstandingPresenceIn, Lancashire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLongstandingPresenceIn Context triple: [Hulton family, hasLongstandingPresenceIn, Lancashire]
-
A.
isLongStanding
Indicates that a relationship, condition, or state has existed for a considerable or extended period of time.
-
B.
hasMultiGenerationalPresenceIn
chosen
Indicates that an entity has maintained a continuous or recurring presence across multiple generations within a specified place or context.
-
C.
hasLargePresenceIn
Indicates that an entity maintains a significant or dominant level of activity, influence, or representation within a specified location, domain, or context.
-
D.
periodOfContinuousInhabitation
Indicates a span of time during which a place is continuously inhabited without interruption.
-
E.
historicalPresence
Indicates that an entity existed, was active, or had a notable presence in a particular place or context during a past time period.
- 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_69f76e559b10819099d6655a6e14587c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff5803c02c81908b63067119f5e684 |
completed | May 9, 2026, 3:51 p.m. |
| PD | Predicate disambiguation | batch_69ff576d8b308190b49a1e072a0ae661 |
completed | May 9, 2026, 3:49 p.m. |
Created at: May 3, 2026, 4:10 p.m.